[{"user_id":"ba8df636-2132-11f1-aed0-ed93e2281fdd","supervisor":[{"first_name":"Christoph","last_name":"Lampert","orcid":"0000-0001-8622-7887","full_name":"Lampert, Christoph","id":"40C20FD2-F248-11E8-B48F-1D18A9856A87"}],"citation":{"apa":"Royer, A. (2020). <i>Leveraging structure in Computer Vision tasks for flexible Deep Learning models</i>. Institute of Science and Technology Austria. <a href=\"https://doi.org/10.15479/AT:ISTA:8390\">https://doi.org/10.15479/AT:ISTA:8390</a>","ama":"Royer A. Leveraging structure in Computer Vision tasks for flexible Deep Learning models. 2020. doi:<a href=\"https://doi.org/10.15479/AT:ISTA:8390\">10.15479/AT:ISTA:8390</a>","chicago":"Royer, Amélie. “Leveraging Structure in Computer Vision Tasks for Flexible Deep Learning Models.” Institute of Science and Technology Austria, 2020. <a href=\"https://doi.org/10.15479/AT:ISTA:8390\">https://doi.org/10.15479/AT:ISTA:8390</a>.","short":"A. Royer, Leveraging Structure in Computer Vision Tasks for Flexible Deep Learning Models, Institute of Science and Technology Austria, 2020.","mla":"Royer, Amélie. <i>Leveraging Structure in Computer Vision Tasks for Flexible Deep Learning Models</i>. Institute of Science and Technology Austria, 2020, doi:<a href=\"https://doi.org/10.15479/AT:ISTA:8390\">10.15479/AT:ISTA:8390</a>.","ieee":"A. Royer, “Leveraging structure in Computer Vision tasks for flexible Deep Learning models,” Institute of Science and Technology Austria, 2020.","ista":"Royer A. 2020. Leveraging structure in Computer Vision tasks for flexible Deep Learning models. Institute of Science and Technology Austria."},"oa":1,"date_published":"2020-09-14T00:00:00Z","OA_place":"publisher","_id":"8390","doi":"10.15479/AT:ISTA:8390","date_created":"2020-09-14T13:42:09Z","author":[{"orcid":"0000-0002-8407-0705","last_name":"Royer","first_name":"Amélie","id":"3811D890-F248-11E8-B48F-1D18A9856A87","full_name":"Royer, Amélie"}],"alternative_title":["ISTA Thesis"],"publication_identifier":{"issn":["2663-337X"],"isbn":["978-3-99078-007-7"]},"acknowledgement":"Last but not least, I would like to acknowledge the support of the IST IT and scientific computing team for helping provide a great work environment.","file_date_updated":"2020-09-14T13:39:17Z","page":"197","title":"Leveraging structure in Computer Vision tasks for flexible Deep Learning models","oa_version":"Published Version","publication_status":"published","abstract":[{"lang":"eng","text":"Deep neural networks have established a new standard for data-dependent feature extraction pipelines in the Computer Vision literature. Despite their remarkable performance in the standard supervised learning scenario, i.e. when models are trained with labeled data and tested on samples that follow a similar distribution, neural networks have been shown to struggle with more advanced generalization abilities, such as transferring knowledge across visually different domains, or generalizing to new unseen combinations of known concepts. In this thesis we argue that, in contrast to the usual black-box behavior of neural networks, leveraging more structured internal representations is a promising direction\r\nfor tackling such problems. In particular, we focus on two forms of structure. First, we tackle modularity: We show that (i) compositional architectures are a natural tool for modeling reasoning tasks, in that they efficiently capture their combinatorial nature, which is key for generalizing beyond the compositions seen during training. We investigate how to to learn such models, both formally and experimentally, for the task of abstract visual reasoning. Then, we show that (ii) in some settings, modularity allows us to efficiently break down complex tasks into smaller, easier, modules, thereby improving computational efficiency; We study this behavior in the context of generative models for colorization, as well as for small objects detection. Secondly, we investigate the inherently layered structure of representations learned by neural networks, and analyze its role in the context of transfer learning and domain adaptation across visually\r\ndissimilar domains. "}],"acknowledged_ssus":[{"_id":"CampIT"},{"_id":"ScienComp"}],"day":"14","degree_awarded":"PhD","month":"09","corr_author":"1","publisher":"Institute of Science and Technology Austria","year":"2020","type":"dissertation","tmp":{"legal_code_url":"https://creativecommons.org/licenses/by-nc-sa/4.0/legalcode","image":"/images/cc_by_nc_sa.png","name":"Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)","short":"CC BY-NC-SA (4.0)"},"department":[{"_id":"ChLa"}],"has_accepted_license":"1","article_processing_charge":"No","status":"public","ddc":["000"],"date_updated":"2026-04-08T07:26:44Z","file":[{"access_level":"open_access","creator":"dernst","date_created":"2020-09-14T13:39:14Z","checksum":"c914d2f88846032f3d8507734861b6ee","file_name":"2020_Thesis_Royer.pdf","file_id":"8391","relation":"main_file","success":1,"date_updated":"2020-09-14T13:39:14Z","file_size":30224591,"content_type":"application/pdf"},{"relation":"main_file","file_name":"thesis_sources.zip","checksum":"ae98fb35d912cff84a89035ae5794d3c","file_id":"8392","date_created":"2020-09-14T13:39:17Z","access_level":"closed","creator":"dernst","date_updated":"2020-09-14T13:39:17Z","file_size":74227627,"content_type":"application/x-zip-compressed"}],"language":[{"iso":"eng"}],"related_material":{"record":[{"relation":"part_of_dissertation","status":"public","id":"7936"},{"relation":"part_of_dissertation","status":"public","id":"8092"},{"id":"911","status":"public","relation":"part_of_dissertation"},{"relation":"part_of_dissertation","id":"8193","status":"public"},{"relation":"part_of_dissertation","id":"7937","status":"public"}]}},{"article_processing_charge":"No","publication":"2020 IEEE Winter Conference on Applications of Computer Vision","department":[{"_id":"ChLa"}],"isi":1,"external_id":{"isi":["000578444802027"],"arxiv":["2008.11995"]},"article_number":"2180-2189","status":"public","date_updated":"2026-04-08T07:26:44Z","related_material":{"record":[{"status":"deleted","id":"8331","relation":"dissertation_contains"},{"status":"public","id":"8390","relation":"dissertation_contains"}]},"language":[{"iso":"eng"}],"day":"01","conference":{"start_date":"2020-03-01","name":"WACV: Winter Conference on Applications of Computer Vision","end_date":"2020-03-05","location":"Snowmass Village, CO, United States"},"publisher":"IEEE","month":"03","type":"conference","year":"2020","quality_controlled":"1","main_file_link":[{"url":"http://arxiv.org/abs/2008.11995","open_access":"1"}],"publication_status":"published","oa_version":"Preprint","title":"A flexible selection scheme for minimum-effort transfer learning","abstract":[{"lang":"eng","text":"Fine-tuning is a popular way of exploiting knowledge contained in a pre-trained convolutional network for a new visual recognition task. However, the orthogonal setting of transferring knowledge from a pretrained network to a visually different yet semantically close source is rarely considered: This commonly happens with real-life data, which is not necessarily as clean as the training source (noise, geometric transformations, different modalities, etc.).To tackle such scenarios, we introduce a new, generalized form of fine-tuning, called flex-tuning, in which any individual unit (e.g. layer) of a network can be tuned, and the most promising one is chosen automatically. In order to make the method appealing for practical use, we propose two lightweight and faster selection procedures that prove to be good approximations in practice. We study these selection criteria empirically across a variety of domain shifts and data scarcity scenarios, and show that fine-tuning individual units, despite its simplicity, yields very good results as an adaptation technique. As it turns out, in contrast to common practice, rather than the last fully-connected unit it is best to tune an intermediate or early one in many domain- shift scenarios, which is accurately detected by flex-tuning."}],"oa":1,"date_published":"2020-03-01T00:00:00Z","citation":{"ista":"Royer A, Lampert C. 2020. A flexible selection scheme for minimum-effort transfer learning. 2020 IEEE Winter Conference on Applications of Computer Vision. WACV: Winter Conference on Applications of Computer Vision, 2180–2189.","ieee":"A. Royer and C. Lampert, “A flexible selection scheme for minimum-effort transfer learning,” in <i>2020 IEEE Winter Conference on Applications of Computer Vision</i>, Snowmass Village, CO, United States, 2020.","ama":"Royer A, Lampert C. A flexible selection scheme for minimum-effort transfer learning. In: <i>2020 IEEE Winter Conference on Applications of Computer Vision</i>. IEEE; 2020. doi:<a href=\"https://doi.org/10.1109/WACV45572.2020.9093635\">10.1109/WACV45572.2020.9093635</a>","chicago":"Royer, Amélie, and Christoph Lampert. “A Flexible Selection Scheme for Minimum-Effort Transfer Learning.” In <i>2020 IEEE Winter Conference on Applications of Computer Vision</i>. IEEE, 2020. <a href=\"https://doi.org/10.1109/WACV45572.2020.9093635\">https://doi.org/10.1109/WACV45572.2020.9093635</a>.","short":"A. Royer, C. Lampert, in:, 2020 IEEE Winter Conference on Applications of Computer Vision, IEEE, 2020.","mla":"Royer, Amélie, and Christoph Lampert. “A Flexible Selection Scheme for Minimum-Effort Transfer Learning.” <i>2020 IEEE Winter Conference on Applications of Computer Vision</i>, 2180–2189, IEEE, 2020, doi:<a href=\"https://doi.org/10.1109/WACV45572.2020.9093635\">10.1109/WACV45572.2020.9093635</a>.","apa":"Royer, A., &#38; Lampert, C. (2020). A flexible selection scheme for minimum-effort transfer learning. In <i>2020 IEEE Winter Conference on Applications of Computer Vision</i>. Snowmass Village, CO, United States: IEEE. <a href=\"https://doi.org/10.1109/WACV45572.2020.9093635\">https://doi.org/10.1109/WACV45572.2020.9093635</a>"},"arxiv":1,"user_id":"317138e5-6ab7-11ef-aa6d-ffef3953e345","doi":"10.1109/WACV45572.2020.9093635","date_created":"2020-06-07T22:00:53Z","author":[{"full_name":"Royer, Amélie","id":"3811D890-F248-11E8-B48F-1D18A9856A87","first_name":"Amélie","orcid":"0000-0002-8407-0705","last_name":"Royer"},{"id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","full_name":"Lampert, Christoph","orcid":"0000-0001-8622-7887","last_name":"Lampert","first_name":"Christoph"}],"_id":"7937","scopus_import":"1","publication_identifier":{"isbn":["9781728165530"]}},{"main_file_link":[{"url":"https://arxiv.org/abs/2004.12623","open_access":"1"}],"quality_controlled":"1","abstract":[{"text":"State-of-the-art detection systems are generally evaluated on their ability to exhaustively retrieve objects densely distributed in the image, across a wide variety of appearances and semantic categories. Orthogonal to this, many real-life object detection applications, for example in remote sensing, instead require dealing with large images that contain only a few small objects of a single class, scattered heterogeneously across the space. In addition, they are often subject to strict computational constraints, such as limited battery capacity and computing power.To tackle these more practical scenarios, we propose a novel flexible detection scheme that efficiently adapts to variable object sizes and densities: We rely on a sequence of detection stages, each of which has the ability to predict groups of objects as well as individuals. Similar to a detection cascade, this multi-stage architecture spares computational effort by discarding large irrelevant regions of the image early during the detection process. The ability to group objects provides further computational and memory savings, as it allows working with lower image resolutions in early stages, where groups are more easily detected than individuals, as they are more salient. We report experimental results on two aerial image datasets, and show that the proposed method is as accurate yet computationally more efficient than standard single-shot detectors, consistently across three different backbone architectures.","lang":"eng"}],"publication_status":"published","oa_version":"Preprint","title":"Localizing grouped instances for efficient detection in low-resource scenarios","doi":"10.1109/WACV45572.2020.9093288","date_created":"2020-06-07T22:00:53Z","author":[{"orcid":"0000-0002-8407-0705","last_name":"Royer","first_name":"Amélie","id":"3811D890-F248-11E8-B48F-1D18A9856A87","full_name":"Royer, Amélie"},{"first_name":"Christoph","last_name":"Lampert","orcid":"0000-0001-8622-7887","full_name":"Lampert, Christoph","id":"40C20FD2-F248-11E8-B48F-1D18A9856A87"}],"scopus_import":1,"_id":"7936","arxiv":1,"citation":{"ieee":"A. Royer and C. Lampert, “Localizing grouped instances for efficient detection in low-resource scenarios,” in <i>IEEE Winter Conference on Applications of Computer Vision</i>,  Snowmass Village, CO, United States, 2020.","ista":"Royer A, Lampert C. 2020. Localizing grouped instances for efficient detection in low-resource scenarios. IEEE Winter Conference on Applications of Computer Vision. WACV: Winter Conference on Applications of Computer Vision, 1716–1725.","apa":"Royer, A., &#38; Lampert, C. (2020). Localizing grouped instances for efficient detection in low-resource scenarios. In <i>IEEE Winter Conference on Applications of Computer Vision</i>.  Snowmass Village, CO, United States: IEEE. <a href=\"https://doi.org/10.1109/WACV45572.2020.9093288\">https://doi.org/10.1109/WACV45572.2020.9093288</a>","ama":"Royer A, Lampert C. Localizing grouped instances for efficient detection in low-resource scenarios. In: <i>IEEE Winter Conference on Applications of Computer Vision</i>. IEEE; 2020. doi:<a href=\"https://doi.org/10.1109/WACV45572.2020.9093288\">10.1109/WACV45572.2020.9093288</a>","short":"A. Royer, C. Lampert, in:, IEEE Winter Conference on Applications of Computer Vision, IEEE, 2020.","mla":"Royer, Amélie, and Christoph Lampert. “Localizing Grouped Instances for Efficient Detection in Low-Resource Scenarios.” <i>IEEE Winter Conference on Applications of Computer Vision</i>, 1716–1725, IEEE, 2020, doi:<a href=\"https://doi.org/10.1109/WACV45572.2020.9093288\">10.1109/WACV45572.2020.9093288</a>.","chicago":"Royer, Amélie, and Christoph Lampert. “Localizing Grouped Instances for Efficient Detection in Low-Resource Scenarios.” In <i>IEEE Winter Conference on Applications of Computer Vision</i>. IEEE, 2020. <a href=\"https://doi.org/10.1109/WACV45572.2020.9093288\">https://doi.org/10.1109/WACV45572.2020.9093288</a>."},"oa":1,"date_published":"2020-03-01T00:00:00Z","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","publication_identifier":{"isbn":["9781728165530"]},"article_number":"1716-1725","external_id":{"arxiv":["2004.12623"]},"status":"public","article_processing_charge":"No","department":[{"_id":"ChLa"}],"publication":"IEEE Winter Conference on Applications of Computer Vision","language":[{"iso":"eng"}],"related_material":{"record":[{"id":"8331","status":"deleted","relation":"dissertation_contains"},{"relation":"dissertation_contains","id":"8390","status":"public"}]},"date_updated":"2026-04-08T07:26:43Z","publisher":"IEEE","conference":{"location":" Snowmass Village, CO, United States","end_date":"2020-03-05","start_date":"2020-03-01","name":"WACV: Winter Conference on Applications of Computer Vision"},"month":"03","day":"01","type":"conference","year":"2020"},{"type":"book_chapter","year":"2020","publisher":"Springer Nature","month":"01","day":"08","related_material":{"record":[{"id":"8331","status":"deleted","relation":"dissertation_contains"},{"relation":"dissertation_contains","status":"public","id":"8390"}]},"language":[{"iso":"eng"}],"date_updated":"2026-04-08T07:26:44Z","editor":[{"last_name":"Singh","first_name":"Richa","full_name":"Singh, Richa"},{"full_name":"Vatsa, Mayank","first_name":"Mayank","last_name":"Vatsa"},{"first_name":"Vishal M.","last_name":"Patel","full_name":"Patel, Vishal M."},{"full_name":"Ratha, Nalini","first_name":"Nalini","last_name":"Ratha"}],"external_id":{"arxiv":["1711.05139"]},"status":"public","article_processing_charge":"No","publication":"Domain Adaptation for Visual Understanding","department":[{"_id":"ChLa"}],"publication_identifier":{"isbn":["9783030306717"]},"author":[{"first_name":"Amélie","orcid":"0000-0002-8407-0705","last_name":"Royer","full_name":"Royer, Amélie","id":"3811D890-F248-11E8-B48F-1D18A9856A87"},{"full_name":"Bousmalis, Konstantinos","last_name":"Bousmalis","first_name":"Konstantinos"},{"full_name":"Gouws, Stephan","first_name":"Stephan","last_name":"Gouws"},{"first_name":"Fred","last_name":"Bertsch","full_name":"Bertsch, Fred"},{"full_name":"Mosseri, Inbar","last_name":"Mosseri","first_name":"Inbar"},{"last_name":"Cole","first_name":"Forrester","full_name":"Cole, Forrester"},{"first_name":"Kevin","last_name":"Murphy","full_name":"Murphy, Kevin"}],"doi":"10.1007/978-3-030-30671-7_3","date_created":"2020-07-05T22:00:46Z","_id":"8092","scopus_import":"1","date_published":"2020-01-08T00:00:00Z","oa":1,"citation":{"ista":"Royer A, Bousmalis K, Gouws S, Bertsch F, Mosseri I, Cole F, Murphy K. 2020.XGAN: Unsupervised image-to-image translation for many-to-many mappings. In: Domain Adaptation for Visual Understanding. , 33–49.","ieee":"A. Royer <i>et al.</i>, “XGAN: Unsupervised image-to-image translation for many-to-many mappings,” in <i>Domain Adaptation for Visual Understanding</i>, R. Singh, M. Vatsa, V. M. Patel, and N. Ratha, Eds. Springer Nature, 2020, pp. 33–49.","short":"A. Royer, K. Bousmalis, S. Gouws, F. Bertsch, I. Mosseri, F. Cole, K. Murphy, in:, R. Singh, M. Vatsa, V.M. Patel, N. Ratha (Eds.), Domain Adaptation for Visual Understanding, Springer Nature, 2020, pp. 33–49.","chicago":"Royer, Amélie, Konstantinos Bousmalis, Stephan Gouws, Fred Bertsch, Inbar Mosseri, Forrester Cole, and Kevin Murphy. “XGAN: Unsupervised Image-to-Image Translation for Many-to-Many Mappings.” In <i>Domain Adaptation for Visual Understanding</i>, edited by Richa Singh, Mayank Vatsa, Vishal M. Patel, and Nalini Ratha, 33–49. Springer Nature, 2020. <a href=\"https://doi.org/10.1007/978-3-030-30671-7_3\">https://doi.org/10.1007/978-3-030-30671-7_3</a>.","mla":"Royer, Amélie, et al. “XGAN: Unsupervised Image-to-Image Translation for Many-to-Many Mappings.” <i>Domain Adaptation for Visual Understanding</i>, edited by Richa Singh et al., Springer Nature, 2020, pp. 33–49, doi:<a href=\"https://doi.org/10.1007/978-3-030-30671-7_3\">10.1007/978-3-030-30671-7_3</a>.","ama":"Royer A, Bousmalis K, Gouws S, et al. XGAN: Unsupervised image-to-image translation for many-to-many mappings. In: Singh R, Vatsa M, Patel VM, Ratha N, eds. <i>Domain Adaptation for Visual Understanding</i>. Springer Nature; 2020:33-49. doi:<a href=\"https://doi.org/10.1007/978-3-030-30671-7_3\">10.1007/978-3-030-30671-7_3</a>","apa":"Royer, A., Bousmalis, K., Gouws, S., Bertsch, F., Mosseri, I., Cole, F., &#38; Murphy, K. (2020). XGAN: Unsupervised image-to-image translation for many-to-many mappings. In R. Singh, M. Vatsa, V. M. Patel, &#38; N. Ratha (Eds.), <i>Domain Adaptation for Visual Understanding</i> (pp. 33–49). Springer Nature. <a href=\"https://doi.org/10.1007/978-3-030-30671-7_3\">https://doi.org/10.1007/978-3-030-30671-7_3</a>"},"arxiv":1,"user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","abstract":[{"lang":"eng","text":"Image translation refers to the task of mapping images from a visual domain to another. Given two unpaired collections of images, we aim to learn a mapping between the corpus-level style of each collection, while preserving semantic content shared across the two domains. We introduce xgan, a dual adversarial auto-encoder, which captures a shared representation of the common domain semantic content in an unsupervised way, while jointly learning the domain-to-domain image translations in both directions. We exploit ideas from the domain adaptation literature and define a semantic consistency loss which encourages the learned embedding to preserve semantics shared across domains. We report promising qualitative results for the task of face-to-cartoon translation. The cartoon dataset we collected for this purpose, “CartoonSet”, is also publicly available as a new benchmark for semantic style transfer at https://google.github.io/cartoonset/index.html."}],"publication_status":"published","title":"XGAN: Unsupervised image-to-image translation for many-to-many mappings","oa_version":"Preprint","page":"33-49","main_file_link":[{"open_access":"1","url":"https://arxiv.org/abs/1711.05139"}],"quality_controlled":"1"},{"external_id":{"arxiv":["1804.04171"]},"status":"public","article_processing_charge":"No","department":[{"_id":"ChLa"}],"language":[{"iso":"eng"}],"related_material":{"record":[{"status":"public","id":"6944","relation":"later_version"}]},"date_updated":"2025-04-15T07:10:25Z","publisher":"Springer Nature","conference":{"location":"Stuttgart, Germany","end_date":"2018-10-12","start_date":"2018-10-09","name":"GCPR: Conference on Pattern Recognition"},"month":"02","day":"14","ec_funded":1,"project":[{"call_identifier":"FP7","name":"Lifelong Learning of Visual Scene Understanding","grant_number":"308036","_id":"2532554C-B435-11E9-9278-68D0E5697425"}],"type":"conference","year":"2019","page":"244-259","main_file_link":[{"open_access":"1","url":"https://arxiv.org/abs/1804.04171"}],"quality_controlled":"1","abstract":[{"text":"Computer vision systems for automatic image categorization have become accurate and reliable enough that they can run continuously for days or even years as components of real-world commercial applications. A major open problem in this context, however, is quality control. Good classification performance can only be expected if systems run under the specific conditions, in particular data distributions, that they were trained for. Surprisingly, none of the currently used deep network architectures have a built-in functionality that could detect if a network operates on data from a distribution it was not trained for, such that potentially a warning to the human users could be triggered. In this work, we describe KS(conf), a procedure for detecting such outside of specifications (out-of-specs) operation, based on statistical testing of the network outputs. We show by extensive experiments using the ImageNet, AwA2 and DAVIS datasets on a variety of ConvNets architectures that KS(conf) reliably detects out-of-specs situations. It furthermore has a number of properties that make it a promising candidate for practical deployment: it is easy to implement, adds almost no overhead to the system, works with all networks, including pretrained ones, and requires no a priori knowledge of how the data distribution could change. ","lang":"eng"}],"publication_status":"published","title":"KS(conf): A light-weight test if a ConvNet operates outside of Its specifications","oa_version":"Preprint","doi":"10.1007/978-3-030-12939-2_18","author":[{"full_name":"Sun, Rémy","last_name":"Sun","first_name":"Rémy"},{"full_name":"Lampert, Christoph","id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","first_name":"Christoph","last_name":"Lampert","orcid":"0000-0001-8622-7887"}],"date_created":"2019-05-24T09:48:36Z","scopus_import":"1","_id":"6482","arxiv":1,"citation":{"apa":"Sun, R., &#38; Lampert, C. (2019). KS(conf): A light-weight test if a ConvNet operates outside of Its specifications (Vol. 11269, pp. 244–259). Presented at the GCPR: Conference on Pattern Recognition, Stuttgart, Germany: Springer Nature. <a href=\"https://doi.org/10.1007/978-3-030-12939-2_18\">https://doi.org/10.1007/978-3-030-12939-2_18</a>","mla":"Sun, Rémy, and Christoph Lampert. <i>KS(Conf): A Light-Weight Test If a ConvNet Operates Outside of Its Specifications</i>. Vol. 11269, Springer Nature, 2019, pp. 244–59, doi:<a href=\"https://doi.org/10.1007/978-3-030-12939-2_18\">10.1007/978-3-030-12939-2_18</a>.","short":"R. Sun, C. Lampert, in:, Springer Nature, 2019, pp. 244–259.","chicago":"Sun, Rémy, and Christoph Lampert. “KS(Conf): A Light-Weight Test If a ConvNet Operates Outside of Its Specifications,” 11269:244–59. Springer Nature, 2019. <a href=\"https://doi.org/10.1007/978-3-030-12939-2_18\">https://doi.org/10.1007/978-3-030-12939-2_18</a>.","ama":"Sun R, Lampert C. KS(conf): A light-weight test if a ConvNet operates outside of Its specifications. In: Vol 11269. Springer Nature; 2019:244-259. doi:<a href=\"https://doi.org/10.1007/978-3-030-12939-2_18\">10.1007/978-3-030-12939-2_18</a>","ieee":"R. Sun and C. Lampert, “KS(conf): A light-weight test if a ConvNet operates outside of Its specifications,” presented at the GCPR: Conference on Pattern Recognition, Stuttgart, Germany, 2019, vol. 11269, pp. 244–259.","ista":"Sun R, Lampert C. 2019. KS(conf): A light-weight test if a ConvNet operates outside of Its specifications. GCPR: Conference on Pattern Recognition, LNCS, vol. 11269, 244–259."},"date_published":"2019-02-14T00:00:00Z","oa":1,"user_id":"c635000d-4b10-11ee-a964-aac5a93f6ac1","intvolume":"     11269","alternative_title":["LNCS"],"volume":11269,"publication_identifier":{"issn":["0302-9743"],"eissn":["1611-3349"],"isbn":["9783030129385","9783030129392"]}},{"oa":1,"date_published":"2019-09-01T00:00:00Z","arxiv":1,"citation":{"ista":"Xian Y, Lampert C, Schiele B, Akata Z. 2019. Zero-shot learning - A comprehensive evaluation of the good, the bad and the ugly. IEEE Transactions on Pattern Analysis and Machine Intelligence. 41(9), 2251–2265.","ieee":"Y. Xian, C. Lampert, B. Schiele, and Z. Akata, “Zero-shot learning - A comprehensive evaluation of the good, the bad and the ugly,” <i>IEEE Transactions on Pattern Analysis and Machine Intelligence</i>, vol. 41, no. 9. Institute of Electrical and Electronics Engineers, pp. 2251–2265, 2019.","chicago":"Xian, Yongqin, Christoph Lampert, Bernt Schiele, and Zeynep Akata. “Zero-Shot Learning - A Comprehensive Evaluation of the Good, the Bad and the Ugly.” <i>IEEE Transactions on Pattern Analysis and Machine Intelligence</i>. Institute of Electrical and Electronics Engineers, 2019. <a href=\"https://doi.org/10.1109/tpami.2018.2857768\">https://doi.org/10.1109/tpami.2018.2857768</a>.","mla":"Xian, Yongqin, et al. “Zero-Shot Learning - A Comprehensive Evaluation of the Good, the Bad and the Ugly.” <i>IEEE Transactions on Pattern Analysis and Machine Intelligence</i>, vol. 41, no. 9, Institute of Electrical and Electronics Engineers, 2019, pp. 2251–65, doi:<a href=\"https://doi.org/10.1109/tpami.2018.2857768\">10.1109/tpami.2018.2857768</a>.","short":"Y. Xian, C. Lampert, B. Schiele, Z. Akata, IEEE Transactions on Pattern Analysis and Machine Intelligence 41 (2019) 2251–2265.","ama":"Xian Y, Lampert C, Schiele B, Akata Z. Zero-shot learning - A comprehensive evaluation of the good, the bad and the ugly. <i>IEEE Transactions on Pattern Analysis and Machine Intelligence</i>. 2019;41(9):2251-2265. doi:<a href=\"https://doi.org/10.1109/tpami.2018.2857768\">10.1109/tpami.2018.2857768</a>","apa":"Xian, Y., Lampert, C., Schiele, B., &#38; Akata, Z. (2019). Zero-shot learning - A comprehensive evaluation of the good, the bad and the ugly. <i>IEEE Transactions on Pattern Analysis and Machine Intelligence</i>. Institute of Electrical and Electronics Engineers. <a href=\"https://doi.org/10.1109/tpami.2018.2857768\">https://doi.org/10.1109/tpami.2018.2857768</a>"},"user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","doi":"10.1109/tpami.2018.2857768","author":[{"first_name":"Yongqin","last_name":"Xian","full_name":"Xian, Yongqin"},{"orcid":"0000-0002-4561-241X","last_name":"Lampert","first_name":"Christoph","id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","full_name":"Lampert, Christoph"},{"first_name":"Bernt","last_name":"Schiele","full_name":"Schiele, Bernt"},{"last_name":"Akata","first_name":"Zeynep","full_name":"Akata, Zeynep"}],"date_created":"2019-06-11T14:05:59Z","_id":"6554","scopus_import":"1","publication_identifier":{"eissn":["1939-3539"],"issn":["0162-8828"]},"volume":41,"article_type":"original","intvolume":"        41","quality_controlled":"1","page":"2251 - 2265","main_file_link":[{"url":"https://arxiv.org/abs/1707.00600","open_access":"1"}],"publication_status":"published","oa_version":"Preprint","title":"Zero-shot learning - A comprehensive evaluation of the good, the bad and the ugly","abstract":[{"text":"Due to the importance of zero-shot learning, i.e. classifying images where there is a lack of labeled training data, the number of proposed approaches has recently increased steadily. We argue that it is time to take a step back and to analyze the status quo of the area. The purpose of this paper is three-fold. First, given the fact that there is no agreed upon zero-shot learning benchmark, we first define a new benchmark by unifying both the evaluation protocols and data splits of publicly available datasets used for this task. This is an important contribution as published results are often not comparable and sometimes even flawed due to, e.g. pre-training on zero-shot test classes. Moreover, we propose a new zero-shot learning dataset, the Animals with Attributes 2 (AWA2) dataset which we make publicly available both in terms of image features and the images themselves. Second, we compare and analyze a significant number of the state-of-the-art methods in depth, both in the classic zero-shot setting but also in the more realistic generalized zero-shot setting. Finally, we discuss in detail the limitations of the current status of the area which can be taken as a basis for advancing it.","lang":"eng"}],"issue":"9","day":"01","publisher":"Institute of Electrical and Electronics Engineers","month":"09","type":"journal_article","year":"2019","article_processing_charge":"No","publication":"IEEE Transactions on Pattern Analysis and Machine Intelligence","department":[{"_id":"ChLa"}],"isi":1,"external_id":{"arxiv":["1707.00600"],"isi":["000480343900015"]},"status":"public","date_updated":"2024-12-11T11:49:58Z","language":[{"iso":"eng"}]},{"day":"13","OA_type":"gold","corr_author":"1","month":"06","conference":{"location":"Long Beach, CA, United States","name":"ICML: International Conference on Machine Learning","start_date":"2019-06-10","end_date":"2019-06-15"},"publisher":"ML Research Press","year":"2019","type":"conference","publication":"Proceedings of the 36th International Conference on Machine Learning","department":[{"_id":"ChLa"}],"has_accepted_license":"1","article_processing_charge":"No","status":"public","ddc":["000"],"date_updated":"2025-05-20T07:48:49Z","file":[{"content_type":"application/pdf","date_updated":"2020-07-14T12:47:33Z","file_size":686432,"access_level":"open_access","creator":"bphuong","file_id":"6570","file_name":"paper.pdf","date_created":"2019-06-20T18:22:56Z","checksum":"a66d00e2694d749250f8507f301320ca","relation":"main_file"}],"language":[{"iso":"eng"}],"user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","oa":1,"date_published":"2019-06-13T00:00:00Z","citation":{"ista":"Phuong M, Lampert C. 2019. Towards understanding knowledge distillation. Proceedings of the 36th International Conference on Machine Learning. ICML: International Conference on Machine Learning vol. 97, 5142–5151.","ieee":"M. Phuong and C. Lampert, “Towards understanding knowledge distillation,” in <i>Proceedings of the 36th International Conference on Machine Learning</i>, Long Beach, CA, United States, 2019, vol. 97, pp. 5142–5151.","mla":"Phuong, Mary, and Christoph Lampert. “Towards Understanding Knowledge Distillation.” <i>Proceedings of the 36th International Conference on Machine Learning</i>, vol. 97, ML Research Press, 2019, pp. 5142–51.","chicago":"Phuong, Mary, and Christoph Lampert. “Towards Understanding Knowledge Distillation.” In <i>Proceedings of the 36th International Conference on Machine Learning</i>, 97:5142–51. ML Research Press, 2019.","short":"M. Phuong, C. Lampert, in:, Proceedings of the 36th International Conference on Machine Learning, ML Research Press, 2019, pp. 5142–5151.","ama":"Phuong M, Lampert C. Towards understanding knowledge distillation. In: <i>Proceedings of the 36th International Conference on Machine Learning</i>. Vol 97. ML Research Press; 2019:5142-5151.","apa":"Phuong, M., &#38; Lampert, C. (2019). Towards understanding knowledge distillation. In <i>Proceedings of the 36th International Conference on Machine Learning</i> (Vol. 97, pp. 5142–5151). Long Beach, CA, United States: ML Research Press."},"_id":"6569","scopus_import":"1","OA_place":"publisher","author":[{"first_name":"Phuong","last_name":"Bui Thi Mai","full_name":"Bui Thi Mai, Phuong","id":"3EC6EE64-F248-11E8-B48F-1D18A9856A87"},{"full_name":"Lampert, Christoph","id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","first_name":"Christoph","orcid":"0000-0001-8622-7887","last_name":"Lampert"}],"date_created":"2019-06-20T18:23:03Z","volume":97,"intvolume":"        97","quality_controlled":"1","file_date_updated":"2020-07-14T12:47:33Z","page":"5142-5151","oa_version":"Published Version","title":"Towards understanding knowledge distillation","publication_status":"published","abstract":[{"text":"Knowledge distillation, i.e. one classifier being trained on the outputs of another classifier, is an empirically very successful technique for knowledge transfer between classifiers. It has even been observed that classifiers learn much faster and more reliably if trained with the outputs of another classifier as soft labels, instead of from ground truth data. So far, however, there is no satisfactory theoretical explanation of this phenomenon. In this work, we provide the first insights into the working mechanisms of distillation by studying the special case of linear and deep linear classifiers.  Specifically,  we prove a generalization bound that establishes fast convergence of the expected risk of a distillation-trained linear classifier. From the bound and its proof we extract three keyfactors that determine the success of distillation: data geometry – geometric properties of the datadistribution, in particular class separation, has an immediate influence on the convergence speed of the risk; optimization bias– gradient descentoptimization finds a very favorable minimum of the distillation objective; and strong monotonicity– the expected risk of the student classifier always decreases when the size of the training set grows.","lang":"eng"}]},{"date_updated":"2025-04-14T13:51:05Z","language":[{"iso":"eng"}],"article_processing_charge":"No","department":[{"_id":"KrCh"},{"_id":"ChLa"}],"isi":1,"publication":"16th International Conference on Quantitative Evaluation of Systems","external_id":{"arxiv":["1906.08178"],"isi":["000679281300007"]},"status":"public","type":"conference","project":[{"_id":"25863FF4-B435-11E9-9278-68D0E5697425","grant_number":"S11407","call_identifier":"FWF","name":"Game Theory"},{"name":"Rigorous Systems Engineering","call_identifier":"FWF","grant_number":"S11402-N23","_id":"25F2ACDE-B435-11E9-9278-68D0E5697425"},{"name":"Efficient Algorithms for Computer Aided Verification","grant_number":"ICT15-003","_id":"25892FC0-B435-11E9-9278-68D0E5697425"}],"year":"2019","day":"04","publisher":"Springer Nature","conference":{"location":"Glasgow, United Kingdom","name":"QEST: Quantitative Evaluation of Systems","start_date":"2019-09-10","end_date":"2019-09-12"},"month":"09","publication_status":"published","title":"Strategy representation by decision trees with linear classifiers","oa_version":"Preprint","abstract":[{"text":"Graph games and Markov decision processes (MDPs) are standard models in reactive synthesis and verification of probabilistic systems with nondeterminism. The class of   𝜔 -regular winning conditions; e.g., safety, reachability, liveness, parity conditions; provides a robust and expressive specification formalism for properties that arise in analysis of reactive systems. The resolutions of nondeterminism in games and MDPs are represented as strategies, and we consider succinct representation of such strategies. The decision-tree data structure from machine learning retains the flavor of decisions of strategies and allows entropy-based minimization to obtain succinct trees. However, in contrast to traditional machine-learning problems where small errors are allowed, for winning strategies in graph games and MDPs no error is allowed, and the decision tree must represent the entire strategy. In this work we propose decision trees with linear classifiers for representation of strategies in graph games and MDPs. We have implemented strategy representation using this data structure and we present experimental results for problems on graph games and MDPs, which show that this new data structure presents a much more efficient strategy representation as compared to standard decision trees.","lang":"eng"}],"quality_controlled":"1","page":"109-128","main_file_link":[{"open_access":"1","url":"https://arxiv.org/abs/1906.08178"}],"alternative_title":["LNCS"],"volume":11785,"publication_identifier":{"isbn":["9783030302801"],"eisbn":["9783030302818"],"issn":["0302-9743"]},"intvolume":"     11785","citation":{"apa":"Ashok, P., Brázdil, T., Chatterjee, K., Křetínský, J., Lampert, C., &#38; Toman, V. (2019). Strategy representation by decision trees with linear classifiers. In <i>16th International Conference on Quantitative Evaluation of Systems</i> (Vol. 11785, pp. 109–128). Glasgow, United Kingdom: Springer Nature. <a href=\"https://doi.org/10.1007/978-3-030-30281-8_7\">https://doi.org/10.1007/978-3-030-30281-8_7</a>","ama":"Ashok P, Brázdil T, Chatterjee K, Křetínský J, Lampert C, Toman V. Strategy representation by decision trees with linear classifiers. In: <i>16th International Conference on Quantitative Evaluation of Systems</i>. Vol 11785. Springer Nature; 2019:109-128. doi:<a href=\"https://doi.org/10.1007/978-3-030-30281-8_7\">10.1007/978-3-030-30281-8_7</a>","mla":"Ashok, Pranav, et al. “Strategy Representation by Decision Trees with Linear Classifiers.” <i>16th International Conference on Quantitative Evaluation of Systems</i>, vol. 11785, Springer Nature, 2019, pp. 109–28, doi:<a href=\"https://doi.org/10.1007/978-3-030-30281-8_7\">10.1007/978-3-030-30281-8_7</a>.","chicago":"Ashok, Pranav, Tomáš Brázdil, Krishnendu Chatterjee, Jan Křetínský, Christoph Lampert, and Viktor Toman. “Strategy Representation by Decision Trees with Linear Classifiers.” In <i>16th International Conference on Quantitative Evaluation of Systems</i>, 11785:109–28. Springer Nature, 2019. <a href=\"https://doi.org/10.1007/978-3-030-30281-8_7\">https://doi.org/10.1007/978-3-030-30281-8_7</a>.","short":"P. Ashok, T. Brázdil, K. Chatterjee, J. Křetínský, C. Lampert, V. Toman, in:, 16th International Conference on Quantitative Evaluation of Systems, Springer Nature, 2019, pp. 109–128.","ieee":"P. Ashok, T. Brázdil, K. Chatterjee, J. Křetínský, C. Lampert, and V. Toman, “Strategy representation by decision trees with linear classifiers,” in <i>16th International Conference on Quantitative Evaluation of Systems</i>, Glasgow, United Kingdom, 2019, vol. 11785, pp. 109–128.","ista":"Ashok P, Brázdil T, Chatterjee K, Křetínský J, Lampert C, Toman V. 2019. Strategy representation by decision trees with linear classifiers. 16th International Conference on Quantitative Evaluation of Systems. QEST: Quantitative Evaluation of Systems, LNCS, vol. 11785, 109–128."},"arxiv":1,"oa":1,"date_published":"2019-09-04T00:00:00Z","user_id":"4359f0d1-fa6c-11eb-b949-802e58b17ae8","doi":"10.1007/978-3-030-30281-8_7","date_created":"2019-10-14T06:57:49Z","author":[{"first_name":"Pranav","last_name":"Ashok","full_name":"Ashok, Pranav"},{"first_name":"Tomáš","last_name":"Brázdil","full_name":"Brázdil, Tomáš"},{"first_name":"Krishnendu","orcid":"0000-0002-4561-241X","last_name":"Chatterjee","full_name":"Chatterjee, Krishnendu","id":"2E5DCA20-F248-11E8-B48F-1D18A9856A87"},{"first_name":"Jan","last_name":"Křetínský","full_name":"Křetínský, Jan"},{"first_name":"Christoph","orcid":"0000-0001-8622-7887","last_name":"Lampert","full_name":"Lampert, Christoph","id":"40C20FD2-F248-11E8-B48F-1D18A9856A87"},{"first_name":"Viktor","orcid":"0000-0001-9036-063X","last_name":"Toman","full_name":"Toman, Viktor","id":"3AF3DA7C-F248-11E8-B48F-1D18A9856A87"}],"scopus_import":"1","_id":"6942"},{"citation":{"ama":"Kersting K, Lampert C, Rothkopf C, eds. <i>Wie Maschinen Lernen: Künstliche Intelligenz Verständlich Erklärt</i>. 1st ed. Wiesbaden: Springer Nature; 2019. doi:<a href=\"https://doi.org/10.1007/978-3-658-26763-6\">10.1007/978-3-658-26763-6</a>","short":"K. Kersting, C. Lampert, C. Rothkopf, eds., Wie Maschinen Lernen: Künstliche Intelligenz Verständlich Erklärt, 1st ed., Springer Nature, Wiesbaden, 2019.","mla":"Kersting, Kristian, et al., editors. <i>Wie Maschinen Lernen: Künstliche Intelligenz Verständlich Erklärt</i>. 1st ed., Springer Nature, 2019, doi:<a href=\"https://doi.org/10.1007/978-3-658-26763-6\">10.1007/978-3-658-26763-6</a>.","chicago":"Kersting, Kristian, Christoph Lampert, and Constantin Rothkopf, eds. <i>Wie Maschinen Lernen: Künstliche Intelligenz Verständlich Erklärt</i>. 1st ed. Wiesbaden: Springer Nature, 2019. <a href=\"https://doi.org/10.1007/978-3-658-26763-6\">https://doi.org/10.1007/978-3-658-26763-6</a>.","apa":"Kersting, K., Lampert, C., &#38; Rothkopf, C. (Eds.). (2019). <i>Wie Maschinen Lernen: Künstliche Intelligenz Verständlich Erklärt</i> (1st ed.). Wiesbaden: Springer Nature. <a href=\"https://doi.org/10.1007/978-3-658-26763-6\">https://doi.org/10.1007/978-3-658-26763-6</a>","ista":"Kersting K, Lampert C, Rothkopf C eds. 2019. Wie Maschinen Lernen: Künstliche Intelligenz Verständlich Erklärt 1st ed., Wiesbaden: Springer Nature, XIV, 245p.","ieee":"K. Kersting, C. Lampert, and C. Rothkopf, Eds., <i>Wie Maschinen Lernen: Künstliche Intelligenz Verständlich Erklärt</i>, 1st ed. Wiesbaden: Springer Nature, 2019."},"date_published":"2019-10-30T00:00:00Z","user_id":"8b945eb4-e2f2-11eb-945a-df72226e66a9","day":"30","publisher":"Springer Nature","doi":"10.1007/978-3-658-26763-6","date_created":"2019-12-11T14:15:56Z","month":"10","_id":"7171","type":"book_editor","year":"2019","publication_identifier":{"isbn":["978-3-658-26762-9"],"eisbn":["978-3-658-26763-6"]},"edition":"1","article_processing_charge":"No","quality_controlled":"1","department":[{"_id":"ChLa"}],"page":"XIV, 245","status":"public","publication_status":"published","date_updated":"2021-12-22T14:40:58Z","place":"Wiesbaden","editor":[{"full_name":"Kersting, Kristian","last_name":"Kersting","first_name":"Kristian"},{"id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","full_name":"Lampert, Christoph","orcid":"0000-0001-8622-7887","last_name":"Lampert","first_name":"Christoph"},{"last_name":"Rothkopf","first_name":"Constantin","full_name":"Rothkopf, Constantin"}],"oa_version":"None","title":"Wie Maschinen Lernen: Künstliche Intelligenz Verständlich Erklärt","language":[{"iso":"ger"}],"related_material":{"link":[{"description":"News on IST Website","relation":"press_release","url":"https://ist.ac.at/en/news/book-release-how-machines-learn/"}]},"abstract":[{"lang":"ger","text":"Wissen Sie, was sich hinter künstlicher Intelligenz und maschinellem Lernen verbirgt? \r\nDieses Sachbuch erklärt Ihnen leicht verständlich und ohne komplizierte Formeln die grundlegenden Methoden und Vorgehensweisen des maschinellen Lernens. Mathematisches Vorwissen ist dafür nicht nötig. Kurzweilig und informativ illustriert Lisa, die Protagonistin des Buches, diese anhand von Alltagssituationen. \r\nEin Buch für alle, die in Diskussionen über Chancen und Risiken der aktuellen Entwicklung der künstlichen Intelligenz und des maschinellen Lernens mit Faktenwissen punkten möchten. Auch für Schülerinnen und Schüler geeignet!"}]},{"article_number":"1749-1753","external_id":{"isi":["000554591601098"],"arxiv":["1807.02136"]},"status":"public","article_processing_charge":"No","department":[{"_id":"ChLa"}],"isi":1,"publication":"Proceedings of the 2019 International Conference on Computer Vision Workshop","language":[{"iso":"eng"}],"date_updated":"2025-04-15T07:10:23Z","publisher":"IEEE","conference":{"name":"ICCVW: International Conference on Computer Vision Workshop","start_date":"2019-10-27","end_date":"2019-10-28","location":"Seoul, South Korea"},"month":"10","day":"01","ec_funded":1,"type":"conference","project":[{"_id":"2532554C-B435-11E9-9278-68D0E5697425","call_identifier":"FP7","name":"Lifelong Learning of Visual Scene Understanding","grant_number":"308036"}],"year":"2019","main_file_link":[{"open_access":"1","url":"https://arxiv.org/abs/1807.02136"}],"quality_controlled":"1","abstract":[{"text":"We propose a new model for detecting visual relationships, such as \"person riding motorcycle\" or \"bottle on table\". This task is an important step towards comprehensive structured mage understanding, going beyond detecting individual objects. Our main novelty is a Box Attention mechanism that allows to model pairwise interactions between objects using standard object detection pipelines. The resulting model is conceptually clean, expressive and relies on well-justified training and prediction procedures. Moreover, unlike previously proposed approaches, our model does not introduce any additional complex components or hyperparameters on top of those already required by the underlying detection model. We conduct an experimental evaluation on two datasets, V-COCO and Open Images, demonstrating strong quantitative and qualitative results.","lang":"eng"}],"publication_status":"published","title":"Detecting visual relationships using box attention","oa_version":"Preprint","date_created":"2020-04-05T22:00:51Z","author":[{"id":"2D157DB6-F248-11E8-B48F-1D18A9856A87","full_name":"Kolesnikov, Alexander","last_name":"Kolesnikov","first_name":"Alexander"},{"full_name":"Kuznetsova, Alina","first_name":"Alina","last_name":"Kuznetsova"},{"full_name":"Lampert, Christoph","id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","first_name":"Christoph","last_name":"Lampert","orcid":"0000-0001-8622-7887"},{"full_name":"Ferrari, Vittorio","first_name":"Vittorio","last_name":"Ferrari"}],"doi":"10.1109/ICCVW.2019.00217","scopus_import":"1","_id":"7640","arxiv":1,"citation":{"chicago":"Kolesnikov, Alexander, Alina Kuznetsova, Christoph Lampert, and Vittorio Ferrari. “Detecting Visual Relationships Using Box Attention.” In <i>Proceedings of the 2019 International Conference on Computer Vision Workshop</i>. IEEE, 2019. <a href=\"https://doi.org/10.1109/ICCVW.2019.00217\">https://doi.org/10.1109/ICCVW.2019.00217</a>.","mla":"Kolesnikov, Alexander, et al. “Detecting Visual Relationships Using Box Attention.” <i>Proceedings of the 2019 International Conference on Computer Vision Workshop</i>, 1749–1753, IEEE, 2019, doi:<a href=\"https://doi.org/10.1109/ICCVW.2019.00217\">10.1109/ICCVW.2019.00217</a>.","short":"A. Kolesnikov, A. Kuznetsova, C. Lampert, V. Ferrari, in:, Proceedings of the 2019 International Conference on Computer Vision Workshop, IEEE, 2019.","ama":"Kolesnikov A, Kuznetsova A, Lampert C, Ferrari V. Detecting visual relationships using box attention. In: <i>Proceedings of the 2019 International Conference on Computer Vision Workshop</i>. IEEE; 2019. doi:<a href=\"https://doi.org/10.1109/ICCVW.2019.00217\">10.1109/ICCVW.2019.00217</a>","apa":"Kolesnikov, A., Kuznetsova, A., Lampert, C., &#38; Ferrari, V. (2019). Detecting visual relationships using box attention. In <i>Proceedings of the 2019 International Conference on Computer Vision Workshop</i>. Seoul, South Korea: IEEE. <a href=\"https://doi.org/10.1109/ICCVW.2019.00217\">https://doi.org/10.1109/ICCVW.2019.00217</a>","ista":"Kolesnikov A, Kuznetsova A, Lampert C, Ferrari V. 2019. Detecting visual relationships using box attention. Proceedings of the 2019 International Conference on Computer Vision Workshop. ICCVW: International Conference on Computer Vision Workshop, 1749–1753.","ieee":"A. Kolesnikov, A. Kuznetsova, C. Lampert, and V. Ferrari, “Detecting visual relationships using box attention,” in <i>Proceedings of the 2019 International Conference on Computer Vision Workshop</i>, Seoul, South Korea, 2019."},"oa":1,"date_published":"2019-10-01T00:00:00Z","user_id":"c635000d-4b10-11ee-a964-aac5a93f6ac1","publication_identifier":{"isbn":["9781728150239"]}},{"user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","date_published":"2019-06-01T00:00:00Z","oa":1,"arxiv":1,"citation":{"ama":"Konstantinov NH, Lampert C. Robust learning from untrusted sources. In: <i>Proceedings of the 36th International Conference on Machine Learning</i>. Vol 97. ML Research Press; 2019:3488-3498.","short":"N.H. Konstantinov, C. Lampert, in:, Proceedings of the 36th International Conference on Machine Learning, ML Research Press, 2019, pp. 3488–3498.","chicago":"Konstantinov, Nikola H, and Christoph Lampert. “Robust Learning from Untrusted Sources.” In <i>Proceedings of the 36th International Conference on Machine Learning</i>, 97:3488–98. ML Research Press, 2019.","mla":"Konstantinov, Nikola H., and Christoph Lampert. “Robust Learning from Untrusted Sources.” <i>Proceedings of the 36th International Conference on Machine Learning</i>, vol. 97, ML Research Press, 2019, pp. 3488–98.","apa":"Konstantinov, N. H., &#38; Lampert, C. (2019). Robust learning from untrusted sources. In <i>Proceedings of the 36th International Conference on Machine Learning</i> (Vol. 97, pp. 3488–3498). Long Beach, CA, USA: ML Research Press.","ista":"Konstantinov NH, Lampert C. 2019. Robust learning from untrusted sources. Proceedings of the 36th International Conference on Machine Learning. ICML: International Conference on Machine Learning vol. 97, 3488–3498.","ieee":"N. H. Konstantinov and C. Lampert, “Robust learning from untrusted sources,” in <i>Proceedings of the 36th International Conference on Machine Learning</i>, Long Beach, CA, USA, 2019, vol. 97, pp. 3488–3498."},"_id":"6590","scopus_import":"1","author":[{"last_name":"Konstantinov","orcid":"0009-0009-5204-7621","first_name":"Nikola H","id":"4B9D76E4-F248-11E8-B48F-1D18A9856A87","full_name":"Konstantinov, Nikola H"},{"first_name":"Christoph","last_name":"Lampert","orcid":"0000-0001-8622-7887","full_name":"Lampert, Christoph","id":"40C20FD2-F248-11E8-B48F-1D18A9856A87"}],"date_created":"2019-06-27T14:18:23Z","volume":97,"intvolume":"        97","quality_controlled":"1","main_file_link":[{"open_access":"1","url":"https://arxiv.org/abs/1901.10310"}],"page":"3488-3498","title":"Robust learning from untrusted sources","oa_version":"Preprint","publication_status":"published","abstract":[{"text":"Modern machine learning methods often require more data for training than a single expert can provide. Therefore, it has become a standard procedure to collect data from external sources, e.g. via crowdsourcing. Unfortunately, the quality of these sources is not always guaranteed. As additional complications, the data might be stored in a distributed way, or might even have to remain private. In this work, we address the question of how to learn robustly in such scenarios. Studying the problem through the lens of statistical learning theory, we derive a procedure that allows for learning from all available sources, yet automatically suppresses irrelevant or corrupted data. We show by extensive experiments that our method provides significant improvements over alternative approaches from robust statistics and distributed optimization. ","lang":"eng"}],"day":"01","month":"06","conference":{"location":"Long Beach, CA, USA","end_date":"2919-06-15","start_date":"2019-06-10","name":"ICML: International Conference on Machine Learning"},"publisher":"ML Research Press","year":"2019","type":"conference","project":[{"grant_number":"308036","name":"Lifelong Learning of Visual Scene Understanding","call_identifier":"FP7","_id":"2532554C-B435-11E9-9278-68D0E5697425"},{"_id":"2564DBCA-B435-11E9-9278-68D0E5697425","call_identifier":"H2020","name":"International IST Doctoral Program","grant_number":"665385"}],"ec_funded":1,"publication":"Proceedings of the 36th International Conference on Machine Learning","department":[{"_id":"ChLa"}],"article_processing_charge":"No","status":"public","external_id":{"arxiv":["1901.10310"]},"date_updated":"2026-04-07T14:19:48Z","related_material":{"record":[{"id":"10799","status":"public","relation":"dissertation_contains"}]},"language":[{"iso":"eng"}]},{"publication_identifier":{"issn":["1550-5499"],"isbn":["9781728148038"]},"volume":"2019-October","citation":{"ista":"Phuong M, Lampert C. 2019. Distillation-based training for multi-exit architectures. IEEE International Conference on Computer Vision. ICCV: International Conference on Computer Vision vol. 2019–October, 1355–1364.","ieee":"M. Phuong and C. Lampert, “Distillation-based training for multi-exit architectures,” in <i>IEEE International Conference on Computer Vision</i>, Seoul, Korea, 2019, vol. 2019–October, pp. 1355–1364.","mla":"Phuong, Mary, and Christoph Lampert. “Distillation-Based Training for Multi-Exit Architectures.” <i>IEEE International Conference on Computer Vision</i>, vol. 2019–October, IEEE, 2019, pp. 1355–64, doi:<a href=\"https://doi.org/10.1109/ICCV.2019.00144\">10.1109/ICCV.2019.00144</a>.","short":"M. Phuong, C. Lampert, in:, IEEE International Conference on Computer Vision, IEEE, 2019, pp. 1355–1364.","chicago":"Phuong, Mary, and Christoph Lampert. “Distillation-Based Training for Multi-Exit Architectures.” In <i>IEEE International Conference on Computer Vision</i>, 2019–October:1355–64. IEEE, 2019. <a href=\"https://doi.org/10.1109/ICCV.2019.00144\">https://doi.org/10.1109/ICCV.2019.00144</a>.","ama":"Phuong M, Lampert C. Distillation-based training for multi-exit architectures. In: <i>IEEE International Conference on Computer Vision</i>. Vol 2019-October. IEEE; 2019:1355-1364. doi:<a href=\"https://doi.org/10.1109/ICCV.2019.00144\">10.1109/ICCV.2019.00144</a>","apa":"Phuong, M., &#38; Lampert, C. (2019). Distillation-based training for multi-exit architectures. In <i>IEEE International Conference on Computer Vision</i> (Vol. 2019–October, pp. 1355–1364). Seoul, Korea: IEEE. <a href=\"https://doi.org/10.1109/ICCV.2019.00144\">https://doi.org/10.1109/ICCV.2019.00144</a>"},"date_published":"2019-10-01T00:00:00Z","oa":1,"user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","date_created":"2020-02-11T09:06:57Z","author":[{"last_name":"Bui Thi Mai","first_name":"Phuong","id":"3EC6EE64-F248-11E8-B48F-1D18A9856A87","full_name":"Bui Thi Mai, Phuong"},{"first_name":"Christoph","orcid":"0000-0001-8622-7887","last_name":"Lampert","full_name":"Lampert, Christoph","id":"40C20FD2-F248-11E8-B48F-1D18A9856A87"}],"doi":"10.1109/ICCV.2019.00144","scopus_import":"1","_id":"7479","publication_status":"published","title":"Distillation-based training for multi-exit architectures","oa_version":"Submitted Version","abstract":[{"lang":"eng","text":"Multi-exit architectures, in which a stack of processing layers is interleaved with early output layers, allow the processing of a test example to stop early and thus save computation time and/or energy.  In this work, we propose a new training procedure for multi-exit architectures based on the principle of knowledge distillation. The method encourage searly exits to mimic later, more accurate exits, by matching their output probabilities.\r\nExperiments  on  CIFAR100  and  ImageNet  show  that distillation-based training significantly improves the accuracy of early exits while maintaining state-of-the-art accuracy  for  late  ones.   The  method  is  particularly  beneficial when  training  data  is  limited  and  it  allows  a  straightforward extension to semi-supervised learning,i.e. making use of unlabeled data at training time. Moreover, it takes only afew lines to implement and incurs almost no computational overhead at training time, and none at all at test time."}],"quality_controlled":"1","file_date_updated":"2020-07-14T12:47:59Z","page":"1355-1364","type":"conference","project":[{"grant_number":"308036","name":"Lifelong Learning of Visual Scene Understanding","call_identifier":"FP7","_id":"2532554C-B435-11E9-9278-68D0E5697425"}],"year":"2019","ec_funded":1,"day":"01","publisher":"IEEE","conference":{"start_date":"2019-10-27","name":"ICCV: International Conference on Computer Vision","end_date":"2019-11-02","location":"Seoul, Korea"},"month":"10","date_updated":"2026-04-08T07:01:16Z","file":[{"date_updated":"2020-07-14T12:47:59Z","file_size":735768,"content_type":"application/pdf","file_id":"7480","checksum":"7b77fb5c2d27c4c37a7612ba46a66117","file_name":"main.pdf","date_created":"2020-02-11T09:06:39Z","access_level":"open_access","creator":"bphuong","relation":"main_file"}],"ddc":["000"],"language":[{"iso":"eng"}],"related_material":{"record":[{"id":"9418","status":"public","relation":"dissertation_contains"}]},"article_processing_charge":"No","has_accepted_license":"1","department":[{"_id":"ChLa"}],"isi":1,"publication":"IEEE International Conference on Computer Vision","external_id":{"isi":["000531438101047"]},"status":"public"},{"type":"journal_article","year":"2018","day":"01","issue":"5","publist_id":"7544","publisher":"IEEE","corr_author":"1","month":"05","file":[{"file_size":141724,"date_updated":"2020-07-14T12:46:03Z","content_type":"application/pdf","relation":"main_file","creator":"dernst","access_level":"open_access","file_id":"7835","file_name":"2018_IEEE_Darrell.pdf","checksum":"b19c75da06faf3291a3ca47dfa50ef63","date_created":"2020-05-14T12:50:48Z"}],"date_updated":"2024-10-09T20:58:26Z","ddc":["000"],"language":[{"iso":"eng"}],"article_processing_charge":"No","publication":"IEEE Transactions on Pattern Analysis and Machine Intelligence","department":[{"_id":"ChLa"}],"has_accepted_license":"1","isi":1,"external_id":{"isi":["000428901200001"]},"status":"public","volume":40,"article_type":"original","intvolume":"        40","date_published":"2018-05-01T00:00:00Z","oa":1,"citation":{"apa":"Darrell, T., Lampert, C., Sebe, N., Wu, Y., &#38; Yan, Y. (2018). Guest editors’ introduction to the special section on learning with Shared information for computer vision and multimedia analysis. <i>IEEE Transactions on Pattern Analysis and Machine Intelligence</i>. IEEE. <a href=\"https://doi.org/10.1109/TPAMI.2018.2804998\">https://doi.org/10.1109/TPAMI.2018.2804998</a>","short":"T. Darrell, C. Lampert, N. Sebe, Y. Wu, Y. Yan, IEEE Transactions on Pattern Analysis and Machine Intelligence 40 (2018) 1029–1031.","mla":"Darrell, Trevor, et al. “Guest Editors’ Introduction to the Special Section on Learning with Shared Information for Computer Vision and Multimedia Analysis.” <i>IEEE Transactions on Pattern Analysis and Machine Intelligence</i>, vol. 40, no. 5, IEEE, 2018, pp. 1029–31, doi:<a href=\"https://doi.org/10.1109/TPAMI.2018.2804998\">10.1109/TPAMI.2018.2804998</a>.","chicago":"Darrell, Trevor, Christoph Lampert, Nico Sebe, Ying Wu, and Yan Yan. “Guest Editors’ Introduction to the Special Section on Learning with Shared Information for Computer Vision and Multimedia Analysis.” <i>IEEE Transactions on Pattern Analysis and Machine Intelligence</i>. IEEE, 2018. <a href=\"https://doi.org/10.1109/TPAMI.2018.2804998\">https://doi.org/10.1109/TPAMI.2018.2804998</a>.","ama":"Darrell T, Lampert C, Sebe N, Wu Y, Yan Y. Guest editors’ introduction to the special section on learning with Shared information for computer vision and multimedia analysis. <i>IEEE Transactions on Pattern Analysis and Machine Intelligence</i>. 2018;40(5):1029-1031. doi:<a href=\"https://doi.org/10.1109/TPAMI.2018.2804998\">10.1109/TPAMI.2018.2804998</a>","ieee":"T. Darrell, C. Lampert, N. Sebe, Y. Wu, and Y. Yan, “Guest editors’ introduction to the special section on learning with Shared information for computer vision and multimedia analysis,” <i>IEEE Transactions on Pattern Analysis and Machine Intelligence</i>, vol. 40, no. 5. IEEE, pp. 1029–1031, 2018.","ista":"Darrell T, Lampert C, Sebe N, Wu Y, Yan Y. 2018. Guest editors’ introduction to the special section on learning with Shared information for computer vision and multimedia analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence. 40(5), 1029–1031."},"user_id":"c635000d-4b10-11ee-a964-aac5a93f6ac1","date_created":"2018-12-11T11:45:48Z","author":[{"first_name":"Trevor","last_name":"Darrell","full_name":"Darrell, Trevor"},{"orcid":"0000-0001-8622-7887","last_name":"Lampert","first_name":"Christoph","id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","full_name":"Lampert, Christoph"},{"full_name":"Sebe, Nico","last_name":"Sebe","first_name":"Nico"},{"full_name":"Wu, Ying","last_name":"Wu","first_name":"Ying"},{"full_name":"Yan, Yan","first_name":"Yan","last_name":"Yan"}],"doi":"10.1109/TPAMI.2018.2804998","_id":"321","scopus_import":"1","publication_status":"published","oa_version":"Published Version","title":"Guest editors' introduction to the special section on learning with Shared information for computer vision and multimedia analysis","abstract":[{"lang":"eng","text":"The twelve papers in this special section focus on learning systems with shared information for computer vision and multimedia communication analysis. In the real world, a realistic setting for computer vision or multimedia recognition problems is that we have some classes containing lots of training data and many classes containing a small amount of training data. Therefore, how to use frequent classes to help learning rare classes for which it is harder to collect the training data is an open question. Learning with shared information is an emerging topic in machine learning, computer vision and multimedia analysis. There are different levels of components that can be shared during concept modeling and machine learning stages, such as sharing generic object parts, sharing attributes, sharing transformations, sharing regularization parameters and sharing training examples, etc. Regarding the specific methods, multi-task learning, transfer learning and deep learning can be seen as using different strategies to share information. These learning with shared information methods are very effective in solving real-world large-scale problems."}],"quality_controlled":"1","file_date_updated":"2020-07-14T12:46:03Z","page":"1029 - 1031"},{"publisher":"IEEE","conference":{"name":"CVF: Conference on Computer Vision and Pattern Recognition","start_date":"2018-06-18","end_date":"2018-06-23","location":"Salt Lake City, UT, United States"},"month":"12","corr_author":"1","day":"17","type":"conference","year":"2018","external_id":{"isi":["000457843609036"],"arxiv":["1712.08087"]},"status":"public","article_processing_charge":"No","department":[{"_id":"ChLa"}],"isi":1,"publication":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition","language":[{"iso":"eng"}],"date_updated":"2024-10-09T21:02:26Z","date_created":"2022-03-18T12:45:09Z","doi":"10.1109/cvpr.2018.00956","author":[{"full_name":"Uijlings, Jasper","last_name":"Uijlings","first_name":"Jasper"},{"full_name":"Konyushkova, Ksenia","first_name":"Ksenia","last_name":"Konyushkova"},{"full_name":"Lampert, Christoph","id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","first_name":"Christoph","last_name":"Lampert","orcid":"0000-0001-8622-7887"},{"first_name":"Vittorio","last_name":"Ferrari","full_name":"Ferrari, Vittorio"}],"scopus_import":"1","_id":"10882","citation":{"short":"J. Uijlings, K. Konyushkova, C. Lampert, V. Ferrari, in:, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, IEEE, 2018, pp. 9175–9184.","chicago":"Uijlings, Jasper, Ksenia Konyushkova, Christoph Lampert, and Vittorio Ferrari. “Learning Intelligent Dialogs for Bounding Box Annotation.” In <i>2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition</i>, 9175–84. IEEE, 2018. <a href=\"https://doi.org/10.1109/cvpr.2018.00956\">https://doi.org/10.1109/cvpr.2018.00956</a>.","mla":"Uijlings, Jasper, et al. “Learning Intelligent Dialogs for Bounding Box Annotation.” <i>2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition</i>, IEEE, 2018, pp. 9175–84, doi:<a href=\"https://doi.org/10.1109/cvpr.2018.00956\">10.1109/cvpr.2018.00956</a>.","ama":"Uijlings J, Konyushkova K, Lampert C, Ferrari V. Learning intelligent dialogs for bounding box annotation. In: <i>2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition</i>. IEEE; 2018:9175-9184. doi:<a href=\"https://doi.org/10.1109/cvpr.2018.00956\">10.1109/cvpr.2018.00956</a>","apa":"Uijlings, J., Konyushkova, K., Lampert, C., &#38; Ferrari, V. (2018). Learning intelligent dialogs for bounding box annotation. In <i>2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition</i> (pp. 9175–9184). Salt Lake City, UT, United States: IEEE. <a href=\"https://doi.org/10.1109/cvpr.2018.00956\">https://doi.org/10.1109/cvpr.2018.00956</a>","ista":"Uijlings J, Konyushkova K, Lampert C, Ferrari V. 2018. Learning intelligent dialogs for bounding box annotation. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. CVF: Conference on Computer Vision and Pattern Recognition, 9175–9184.","ieee":"J. Uijlings, K. Konyushkova, C. Lampert, and V. Ferrari, “Learning intelligent dialogs for bounding box annotation,” in <i>2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition</i>, Salt Lake City, UT, United States, 2018, pp. 9175–9184."},"arxiv":1,"oa":1,"date_published":"2018-12-17T00:00:00Z","user_id":"c635000d-4b10-11ee-a964-aac5a93f6ac1","publication_identifier":{"isbn":["9781538664209"],"eissn":["2575-7075"]},"page":"9175-9184","main_file_link":[{"open_access":"1","url":" https://doi.org/10.48550/arXiv.1712.08087"}],"quality_controlled":"1","abstract":[{"text":"We introduce Intelligent Annotation Dialogs for bounding box annotation. We train an agent to automatically choose a sequence of actions for a human annotator to produce a bounding box in a minimal amount of time. Specifically, we consider two actions: box verification [34], where the annotator verifies a box generated by an object detector, and manual box drawing. We explore two kinds of agents, one based on predicting the probability that a box will be positively verified, and the other based on reinforcement learning. We demonstrate that (1) our agents are able to learn efficient annotation strategies in several scenarios, automatically adapting to the image difficulty, the desired quality of the boxes, and the detector strength; (2) in all scenarios the resulting annotation dialogs speed up annotation compared to manual box drawing alone and box verification alone, while also outperforming any fixed combination of verification and drawing in most scenarios; (3) in a realistic scenario where the detector is iteratively re-trained, our agents evolve a series of strategies that reflect the shifting trade-off between verification and drawing as the detector grows stronger.","lang":"eng"}],"publication_status":"published","title":"Learning intelligent dialogs for bounding box annotation","oa_version":"Preprint"},{"department":[{"_id":"ChLa"},{"_id":"GaTk"}],"has_accepted_license":"1","file_date_updated":"2020-07-14T12:47:07Z","article_processing_charge":"No","status":"public","oa_version":"Published Version","title":"Nonlinear decoding of a complex movie from the mammalian retina","date_updated":"2025-04-15T08:18:24Z","ddc":["570"],"file":[{"content_type":"application/octet-stream","date_updated":"2020-07-14T12:47:07Z","file_size":1142543971,"relation":"main_file","checksum":"6808748837b9afbbbabc2a356ca2b88a","file_name":"IST-2018-98-v1+1_BBalls_area2_tile2_20x20.mat","file_id":"5590","date_created":"2018-12-12T13:02:24Z","creator":"system","access_level":"open_access"},{"relation":"main_file","access_level":"open_access","creator":"system","date_created":"2018-12-12T13:02:25Z","file_name":"IST-2018-98-v1+2_ExperimentStructure.pdf","checksum":"d6d6cd07743038fe3a12352983fcf9dd","file_id":"5591","content_type":"application/pdf","file_size":702336,"date_updated":"2020-07-14T12:47:07Z"},{"relation":"main_file","date_created":"2018-12-12T13:02:26Z","file_name":"IST-2018-98-v1+3_GoodLocations_area2_20x20.mat","checksum":"0c9cfb4dab35bb3dc25a04395600b1c8","file_id":"5592","creator":"system","access_level":"open_access","date_updated":"2020-07-14T12:47:07Z","file_size":432,"content_type":"application/octet-stream"},{"access_level":"open_access","creator":"system","date_created":"2018-12-12T13:02:26Z","checksum":"2a83b011012e21e934b4596285b1a183","file_id":"5593","file_name":"IST-2018-98-v1+4_README.txt","relation":"main_file","date_updated":"2020-07-14T12:47:07Z","file_size":986,"content_type":"text/plain"}],"abstract":[{"lang":"eng","text":"This package contains data for the publication \"Nonlinear decoding of a complex movie from the mammalian retina\" by Deny S. et al, PLOS Comput Biol (2018). \r\n\r\nThe data consists of\r\n(i) 91 spike sorted, isolated rat retinal ganglion cells that pass stability and quality criteria, recorded on the multi-electrode array, in response to the presentation of the complex movie with many randomly moving dark discs. The responses are represented as 648000 x 91 binary matrix, where the first index indicates the timebin of duration 12.5 ms, and the second index the neural identity. The matrix entry is 0/1 if the neuron didn't/did spike in the particular time bin.\r\n(ii) README file and a graphical illustration of the structure of the experiment, specifying how the 648000 timebins are split into epochs where 1, 2, 4, or 10 discs  were displayed, and which stimulus segments are exact repeats or unique ball trajectories.\r\n(iii) a 648000 x 400 matrix of luminance traces for each of the 20 x 20 positions (\"sites\") in the movie frame, with time that is locked to the recorded raster. The luminance traces are produced as described in the manuscript by filtering the raw disc movie with a small gaussian spatial kernel. "}],"related_material":{"record":[{"status":"public","id":"292","relation":"used_in_publication"}]},"license":"https://creativecommons.org/publicdomain/zero/1.0/","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","day":"29","citation":{"ieee":"S. Deny, O. Marre, V. Botella-Soler, G. S. Martius, and G. Tkačik, “Nonlinear decoding of a complex movie from the mammalian retina.” Institute of Science and Technology Austria, 2018.","ista":"Deny S, Marre O, Botella-Soler V, Martius GS, Tkačik G. 2018. Nonlinear decoding of a complex movie from the mammalian retina, Institute of Science and Technology Austria, <a href=\"https://doi.org/10.15479/AT:ISTA:98\">10.15479/AT:ISTA:98</a>.","apa":"Deny, S., Marre, O., Botella-Soler, V., Martius, G. S., &#38; Tkačik, G. (2018). Nonlinear decoding of a complex movie from the mammalian retina. Institute of Science and Technology Austria. <a href=\"https://doi.org/10.15479/AT:ISTA:98\">https://doi.org/10.15479/AT:ISTA:98</a>","ama":"Deny S, Marre O, Botella-Soler V, Martius GS, Tkačik G. Nonlinear decoding of a complex movie from the mammalian retina. 2018. doi:<a href=\"https://doi.org/10.15479/AT:ISTA:98\">10.15479/AT:ISTA:98</a>","chicago":"Deny, Stephane, Olivier Marre, Vicente Botella-Soler, Georg S Martius, and Gašper Tkačik. “Nonlinear Decoding of a Complex Movie from the Mammalian Retina.” Institute of Science and Technology Austria, 2018. <a href=\"https://doi.org/10.15479/AT:ISTA:98\">https://doi.org/10.15479/AT:ISTA:98</a>.","mla":"Deny, Stephane, et al. <i>Nonlinear Decoding of a Complex Movie from the Mammalian Retina</i>. Institute of Science and Technology Austria, 2018, doi:<a href=\"https://doi.org/10.15479/AT:ISTA:98\">10.15479/AT:ISTA:98</a>.","short":"S. Deny, O. Marre, V. Botella-Soler, G.S. Martius, G. Tkačik, (2018)."},"oa":1,"date_published":"2018-03-29T00:00:00Z","month":"03","_id":"5584","datarep_id":"98","publisher":"Institute of Science and Technology Austria","date_created":"2018-12-12T12:31:39Z","doi":"10.15479/AT:ISTA:98","author":[{"first_name":"Stephane","last_name":"Deny","full_name":"Deny, Stephane"},{"full_name":"Marre, Olivier","first_name":"Olivier","last_name":"Marre"},{"full_name":"Botella-Soler, Vicente","last_name":"Botella-Soler","first_name":"Vicente"},{"last_name":"Martius","first_name":"Georg S","id":"3A276B68-F248-11E8-B48F-1D18A9856A87","full_name":"Martius, Georg S"},{"last_name":"Tkacik","orcid":"0000-0002-6699-1455","first_name":"Gasper","id":"3D494DCA-F248-11E8-B48F-1D18A9856A87","full_name":"Tkacik, Gasper"}],"year":"2018","project":[{"_id":"254D1A94-B435-11E9-9278-68D0E5697425","grant_number":"P 25651-N26","name":"Sensitivity to higher-order statistics in natural scenes","call_identifier":"FWF"}],"type":"research_data","tmp":{"legal_code_url":"https://creativecommons.org/publicdomain/zero/1.0/legalcode","image":"/images/cc_0.png","name":"Creative Commons Public Domain Dedication (CC0 1.0)","short":"CC0 (1.0)"},"keyword":["retina","decoding","regression","neural networks","complex stimulus"]},{"_id":"6011","scopus_import":"1","author":[{"full_name":"Kuzborskij, Ilja","last_name":"Kuzborskij","first_name":"Ilja"},{"id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","full_name":"Lampert, Christoph","orcid":"0000-0001-8622-7887","last_name":"Lampert","first_name":"Christoph"}],"date_created":"2019-02-14T14:51:57Z","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","date_published":"2018-02-01T00:00:00Z","oa":1,"citation":{"ieee":"I. Kuzborskij and C. Lampert, “Data-dependent stability of stochastic gradient descent,” in <i>Proceedings of the 35 th International Conference on Machine Learning</i>, Stockholm, Sweden, 2018, vol. 80, pp. 2815–2824.","ista":"Kuzborskij I, Lampert C. 2018. Data-dependent stability of stochastic gradient descent. Proceedings of the 35 th International Conference on Machine Learning. ICML: International Conference on Machine Learning vol. 80, 2815–2824.","apa":"Kuzborskij, I., &#38; Lampert, C. (2018). Data-dependent stability of stochastic gradient descent. In <i>Proceedings of the 35 th International Conference on Machine Learning</i> (Vol. 80, pp. 2815–2824). Stockholm, Sweden: ML Research Press.","chicago":"Kuzborskij, Ilja, and Christoph Lampert. “Data-Dependent Stability of Stochastic Gradient Descent.” In <i>Proceedings of the 35 Th International Conference on Machine Learning</i>, 80:2815–24. ML Research Press, 2018.","mla":"Kuzborskij, Ilja, and Christoph Lampert. “Data-Dependent Stability of Stochastic Gradient Descent.” <i>Proceedings of the 35 Th International Conference on Machine Learning</i>, vol. 80, ML Research Press, 2018, pp. 2815–24.","short":"I. Kuzborskij, C. Lampert, in:, Proceedings of the 35 Th International Conference on Machine Learning, ML Research Press, 2018, pp. 2815–2824.","ama":"Kuzborskij I, Lampert C. Data-dependent stability of stochastic gradient descent. In: <i>Proceedings of the 35 Th International Conference on Machine Learning</i>. Vol 80. ML Research Press; 2018:2815-2824."},"arxiv":1,"intvolume":"        80","volume":80,"main_file_link":[{"open_access":"1","url":"https://arxiv.org/abs/1703.01678"}],"page":"2815-2824","quality_controlled":"1","abstract":[{"lang":"eng","text":"We establish a data-dependent notion of algorithmic stability for Stochastic Gradient Descent (SGD), and employ it to develop novel generalization bounds. This is in contrast to previous distribution-free algorithmic stability results for SGD which depend on the worst-case constants. By virtue of the data-dependent argument, our bounds provide new insights into learning with SGD on convex and non-convex problems. In the convex case, we show that the bound on the generalization error depends on the risk at the initialization point. In the non-convex case, we prove that the expected curvature of the objective function around the initialization point has crucial influence on the generalization error. In both cases, our results suggest a simple data-driven strategy to stabilize SGD by pre-screening its initialization. As a corollary, our results allow us to show optimistic generalization bounds that exhibit fast convergence rates for SGD subject to a vanishing empirical risk and low noise of stochastic gradient. "}],"title":"Data-dependent stability of stochastic gradient descent","oa_version":"Preprint","publication_status":"published","month":"02","conference":{"location":"Stockholm, Sweden","end_date":"2018-07-15","name":"ICML: International Conference on Machine Learning","start_date":"2018-07-10"},"publisher":"ML Research Press","day":"01","ec_funded":1,"year":"2018","project":[{"_id":"2532554C-B435-11E9-9278-68D0E5697425","call_identifier":"FP7","name":"Lifelong Learning of Visual Scene Understanding","grant_number":"308036"}],"type":"conference","status":"public","external_id":{"isi":["000683379202095"],"arxiv":["1703.01678"]},"publication":"Proceedings of the 35 th International Conference on Machine Learning","isi":1,"department":[{"_id":"ChLa"}],"article_processing_charge":"No","language":[{"iso":"eng"}],"date_updated":"2025-04-15T07:10:23Z"},{"ec_funded":1,"type":"conference","project":[{"_id":"25681D80-B435-11E9-9278-68D0E5697425","call_identifier":"FP7","name":"International IST Postdoc Fellowship Programme","grant_number":"291734"}],"year":"2018","conference":{"start_date":"2018-07-10","name":"ICML: International Conference on Machine Learning","end_date":"2018-07-15","location":"Stockholm, Sweden"},"publisher":"ML Research Press","month":"02","day":"01","related_material":{"link":[{"description":"News on IST Homepage","url":"https://ist.ac.at/en/news/first-machine-learning-method-capable-of-accurate-extrapolation/","relation":"press_release"}]},"language":[{"iso":"eng"}],"date_updated":"2025-04-15T06:50:24Z","external_id":{"arxiv":["1806.07259"],"isi":["000683379204058"]},"status":"public","article_processing_charge":"No","publication":"Proceedings of the 35th International Conference on Machine Learning","department":[{"_id":"ChLa"}],"isi":1,"intvolume":"        80","volume":80,"author":[{"full_name":"Sahoo, Subham","last_name":"Sahoo","first_name":"Subham"},{"last_name":"Lampert","orcid":"0000-0001-8622-7887","first_name":"Christoph","id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","full_name":"Lampert, Christoph"},{"id":"3A276B68-F248-11E8-B48F-1D18A9856A87","full_name":"Martius, Georg S","last_name":"Martius","first_name":"Georg S"}],"date_created":"2019-02-14T15:21:07Z","_id":"6012","scopus_import":"1","oa":1,"date_published":"2018-02-01T00:00:00Z","citation":{"ama":"Sahoo S, Lampert C, Martius GS. Learning equations for extrapolation and control. In: <i>Proceedings of the 35th International Conference on Machine Learning</i>. Vol 80. ML Research Press; 2018:4442-4450.","chicago":"Sahoo, Subham, Christoph Lampert, and Georg S Martius. “Learning Equations for Extrapolation and Control.” In <i>Proceedings of the 35th International Conference on Machine Learning</i>, 80:4442–50. ML Research Press, 2018.","short":"S. Sahoo, C. Lampert, G.S. Martius, in:, Proceedings of the 35th International Conference on Machine Learning, ML Research Press, 2018, pp. 4442–4450.","mla":"Sahoo, Subham, et al. “Learning Equations for Extrapolation and Control.” <i>Proceedings of the 35th International Conference on Machine Learning</i>, vol. 80, ML Research Press, 2018, pp. 4442–50.","apa":"Sahoo, S., Lampert, C., &#38; Martius, G. S. (2018). Learning equations for extrapolation and control. In <i>Proceedings of the 35th International Conference on Machine Learning</i> (Vol. 80, pp. 4442–4450). Stockholm, Sweden: ML Research Press.","ista":"Sahoo S, Lampert C, Martius GS. 2018. Learning equations for extrapolation and control. Proceedings of the 35th International Conference on Machine Learning. ICML: International Conference on Machine Learning vol. 80, 4442–4450.","ieee":"S. Sahoo, C. Lampert, and G. S. Martius, “Learning equations for extrapolation and control,” in <i>Proceedings of the 35th International Conference on Machine Learning</i>, Stockholm, Sweden, 2018, vol. 80, pp. 4442–4450."},"arxiv":1,"user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","abstract":[{"lang":"eng","text":"We present an approach to identify concise equations from data using a shallow neural network approach. In contrast to ordinary black-box regression, this approach allows understanding functional relations and generalizing them from observed data to unseen parts of the parameter space. We show how to extend the class of learnable equations for a recently proposed equation learning network to include divisions, and we improve the learning and model selection strategy to be useful for challenging real-world data. For systems governed by analytical expressions, our method can in many cases identify the true underlying equation and extrapolate to unseen domains. We demonstrate its effectiveness by experiments on a cart-pendulum system, where only 2 random rollouts are required to learn the forward dynamics and successfully achieve the swing-up task."}],"publication_status":"published","title":"Learning equations for extrapolation and control","oa_version":"Preprint","page":"4442-4450","main_file_link":[{"url":"https://arxiv.org/abs/1806.07259","open_access":"1"}],"quality_controlled":"1"},{"article_processing_charge":"No","department":[{"_id":"DaAl"},{"_id":"ChLa"}],"isi":1,"publication":"Advances in Neural Information Processing Systems 31","external_id":{"isi":["000461852000047"],"arxiv":["1809.10505"]},"status":"public","date_updated":"2025-06-26T12:23:06Z","language":[{"iso":"eng"}],"day":"01","publisher":"Neural Information Processing Systems Foundation","conference":{"start_date":"2018-12-02","name":"NeurIPS: Conference on Neural Information Processing Systems","end_date":"2018-12-08","location":"Montreal, Canada"},"month":"12","corr_author":"1","project":[{"_id":"2564DBCA-B435-11E9-9278-68D0E5697425","grant_number":"665385","call_identifier":"H2020","name":"International IST Doctoral Program"}],"type":"conference","year":"2018","ec_funded":1,"quality_controlled":"1","page":"5973-5983","main_file_link":[{"url":"https://arxiv.org/abs/1809.10505","open_access":"1"}],"publication_status":"published","oa_version":"Preprint","title":"The convergence of sparsified gradient methods","abstract":[{"lang":"eng","text":"Distributed training of massive machine learning models, in particular deep neural networks, via Stochastic Gradient Descent (SGD) is becoming commonplace. Several families of communication-reduction methods, such as quantization, large-batch methods, and gradient sparsification, have been proposed. To date, gradient sparsification methods--where each node sorts gradients by magnitude, and only communicates a subset of the components, accumulating the rest locally--are known to yield some of the largest practical gains. Such methods can reduce the amount of communication per step by up to \\emph{three orders of magnitude}, while preserving model accuracy. Yet, this family of methods currently has no theoretical justification. This is the question we address in this paper. We prove that, under analytic assumptions, sparsifying gradients by magnitude with local error correction provides convergence guarantees, for both convex and non-convex smooth objectives, for data-parallel SGD. The main insight is that sparsification methods implicitly maintain bounds on the maximum impact of stale updates, thanks to selection by magnitude. Our analysis and empirical validation also reveal that these methods do require analytical conditions to converge well, justifying existing heuristics."}],"arxiv":1,"citation":{"ieee":"D.-A. Alistarh, T. Hoefler, M. Johansson, N. H. Konstantinov, S. Khirirat, and C. Renggli, “The convergence of sparsified gradient methods,” in <i>Advances in Neural Information Processing Systems 31</i>, Montreal, Canada, 2018, vol. Volume 2018, pp. 5973–5983.","ista":"Alistarh D-A, Hoefler T, Johansson M, Konstantinov NH, Khirirat S, Renggli C. 2018. The convergence of sparsified gradient methods. Advances in Neural Information Processing Systems 31. NeurIPS: Conference on Neural Information Processing Systems vol. Volume 2018, 5973–5983.","apa":"Alistarh, D.-A., Hoefler, T., Johansson, M., Konstantinov, N. H., Khirirat, S., &#38; Renggli, C. (2018). The convergence of sparsified gradient methods. In <i>Advances in Neural Information Processing Systems 31</i> (Vol. Volume 2018, pp. 5973–5983). Montreal, Canada: Neural Information Processing Systems Foundation.","chicago":"Alistarh, Dan-Adrian, Torsten Hoefler, Mikael Johansson, Nikola H Konstantinov, Sarit Khirirat, and Cedric Renggli. “The Convergence of Sparsified Gradient Methods.” In <i>Advances in Neural Information Processing Systems 31</i>, Volume 2018:5973–83. Neural Information Processing Systems Foundation, 2018.","mla":"Alistarh, Dan-Adrian, et al. “The Convergence of Sparsified Gradient Methods.” <i>Advances in Neural Information Processing Systems 31</i>, vol. Volume 2018, Neural Information Processing Systems Foundation, 2018, pp. 5973–83.","short":"D.-A. Alistarh, T. Hoefler, M. Johansson, N.H. Konstantinov, S. Khirirat, C. Renggli, in:, Advances in Neural Information Processing Systems 31, Neural Information Processing Systems Foundation, 2018, pp. 5973–5983.","ama":"Alistarh D-A, Hoefler T, Johansson M, Konstantinov NH, Khirirat S, Renggli C. The convergence of sparsified gradient methods. In: <i>Advances in Neural Information Processing Systems 31</i>. Vol Volume 2018. Neural Information Processing Systems Foundation; 2018:5973-5983."},"oa":1,"date_published":"2018-12-01T00:00:00Z","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","date_created":"2019-06-27T09:32:55Z","author":[{"full_name":"Alistarh, Dan-Adrian","id":"4A899BFC-F248-11E8-B48F-1D18A9856A87","first_name":"Dan-Adrian","orcid":"0000-0003-3650-940X","last_name":"Alistarh"},{"first_name":"Torsten","last_name":"Hoefler","full_name":"Hoefler, Torsten"},{"first_name":"Mikael","last_name":"Johansson","full_name":"Johansson, Mikael"},{"first_name":"Nikola H","last_name":"Konstantinov","full_name":"Konstantinov, Nikola H","id":"4B9D76E4-F248-11E8-B48F-1D18A9856A87"},{"full_name":"Khirirat, Sarit","last_name":"Khirirat","first_name":"Sarit"},{"last_name":"Renggli","first_name":"Cedric","full_name":"Renggli, Cedric"}],"scopus_import":"1","_id":"6589","volume":"Volume 2018"},{"abstract":[{"lang":"eng","text":"Modern computer vision systems heavily rely on statistical machine learning models, which typically require large amounts of labeled data to be learned reliably. Moreover, very recently computer vision research widely adopted techniques for representation learning, which further increase the demand for labeled data. However, for many important practical problems there is relatively small amount of labeled data available, so it is problematic to leverage full potential of the representation learning methods. One way to overcome this obstacle is to invest substantial resources into producing large labelled datasets. Unfortunately, this can be prohibitively expensive in practice. In this thesis we focus on the alternative way of tackling the aforementioned issue. We concentrate on methods, which make use of weakly-labeled or even unlabeled data. Specifically, the first half of the thesis is dedicated to the semantic image segmentation task. We develop a technique, which achieves competitive segmentation performance and only requires annotations in a form of global image-level labels instead of dense segmentation masks. Subsequently, we present a new methodology, which further improves segmentation performance by leveraging tiny additional feedback from a human annotator. By using our methods practitioners can greatly reduce the amount of data annotation effort, which is required to learn modern image segmentation models. In the second half of the thesis we focus on methods for learning from unlabeled visual data. We study a family of autoregressive models for modeling structure of natural images and discuss potential applications of these models. Moreover, we conduct in-depth study of one of these applications, where we develop the state-of-the-art model for the probabilistic image colorization task."}],"publication_status":"published","title":"Weakly-Supervised Segmentation and Unsupervised Modeling of Natural Images","oa_version":"Published Version","page":"113","file_date_updated":"2020-07-14T12:45:22Z","acknowledgement":"I also gratefully acknowledge the support of NVIDIA Corporation with the donation of the GPUs used for this research.","alternative_title":["ISTA Thesis"],"publication_identifier":{"issn":["2663-337X"]},"author":[{"full_name":"Kolesnikov, Alexander","id":"2D157DB6-F248-11E8-B48F-1D18A9856A87","first_name":"Alexander","last_name":"Kolesnikov"}],"doi":"10.15479/AT:ISTA:th_1021","date_created":"2018-12-11T11:45:09Z","OA_place":"publisher","_id":"197","supervisor":[{"full_name":"Lampert, Christoph","id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","first_name":"Christoph","orcid":"0000-0001-8622-7887","last_name":"Lampert"}],"citation":{"ista":"Kolesnikov A. 2018. Weakly-Supervised Segmentation and Unsupervised Modeling of Natural Images. Institute of Science and Technology Austria.","ieee":"A. Kolesnikov, “Weakly-Supervised Segmentation and Unsupervised Modeling of Natural Images,” Institute of Science and Technology Austria, 2018.","ama":"Kolesnikov A. Weakly-Supervised Segmentation and Unsupervised Modeling of Natural Images. 2018. doi:<a href=\"https://doi.org/10.15479/AT:ISTA:th_1021\">10.15479/AT:ISTA:th_1021</a>","short":"A. Kolesnikov, Weakly-Supervised Segmentation and Unsupervised Modeling of Natural Images, Institute of Science and Technology Austria, 2018.","mla":"Kolesnikov, Alexander. <i>Weakly-Supervised Segmentation and Unsupervised Modeling of Natural Images</i>. Institute of Science and Technology Austria, 2018, doi:<a href=\"https://doi.org/10.15479/AT:ISTA:th_1021\">10.15479/AT:ISTA:th_1021</a>.","chicago":"Kolesnikov, Alexander. “Weakly-Supervised Segmentation and Unsupervised Modeling of Natural Images.” Institute of Science and Technology Austria, 2018. <a href=\"https://doi.org/10.15479/AT:ISTA:th_1021\">https://doi.org/10.15479/AT:ISTA:th_1021</a>.","apa":"Kolesnikov, A. (2018). <i>Weakly-Supervised Segmentation and Unsupervised Modeling of Natural Images</i>. Institute of Science and Technology Austria. <a href=\"https://doi.org/10.15479/AT:ISTA:th_1021\">https://doi.org/10.15479/AT:ISTA:th_1021</a>"},"oa":1,"date_published":"2018-05-25T00:00:00Z","user_id":"ba8df636-2132-11f1-aed0-ed93e2281fdd","language":[{"iso":"eng"}],"ddc":["004"],"date_updated":"2026-04-08T14:05:16Z","file":[{"content_type":"application/pdf","date_updated":"2020-07-14T12:45:22Z","file_size":12918758,"file_id":"5113","checksum":"bc678e02468d8ebc39dc7267dfb0a1c4","date_created":"2018-12-12T10:14:57Z","file_name":"IST-2018-1021-v1+1_thesis-unsigned-pdfa.pdf","access_level":"open_access","creator":"system","relation":"main_file"},{"file_name":"2018_Thesis_Kolesnikov_source.zip","date_created":"2019-04-05T09:34:49Z","file_id":"6225","checksum":"bc66973b086da5a043f1162dcfb1fde4","access_level":"closed","creator":"dernst","relation":"source_file","date_updated":"2020-07-14T12:45:22Z","file_size":55973760,"content_type":"application/zip"}],"status":"public","article_processing_charge":"No","department":[{"_id":"ChLa"}],"has_accepted_license":"1","ec_funded":1,"pubrep_id":"1021","project":[{"_id":"2532554C-B435-11E9-9278-68D0E5697425","grant_number":"308036","call_identifier":"FP7","name":"Lifelong Learning of Visual Scene Understanding"}],"type":"dissertation","year":"2018","publisher":"Institute of Science and Technology Austria","month":"05","corr_author":"1","degree_awarded":"PhD","day":"25","publist_id":"7718"},{"publication_status":"published","oa_version":"Published Version","title":"Learning from dependent data","abstract":[{"lang":"eng","text":"The most common assumption made in statistical learning theory is the assumption of the independent and identically distributed (i.i.d.) data. While being very convenient mathematically, it is often very clearly violated in practice. This disparity between the machine learning theory and applications underlies a growing demand in the development of algorithms that learn from dependent data and theory that can provide generalization guarantees similar to the independent situations. This thesis is dedicated to two variants of dependencies that can arise in practice. One is a dependence on the level of samples in a single learning task. Another dependency type arises in the multi-task setting when the tasks are dependent on each other even though the data for them can be i.i.d. In both cases we model the data (samples or tasks) as stochastic processes and introduce new algorithms for both settings that take into account and exploit the resulting dependencies. We prove the theoretical guarantees on the performance of the introduced algorithms under different evaluation criteria and, in addition, we compliment the theoretical study by the empirical one, where we evaluate some of the algorithms on two real world datasets to highlight their practical applicability."}],"file_date_updated":"2020-07-14T12:47:40Z","page":"92","publication_identifier":{"issn":["2663-337X"]},"alternative_title":["ISTA Thesis"],"oa":1,"date_published":"2018-09-01T00:00:00Z","citation":{"ista":"Zimin A. 2018. Learning from dependent data. Institute of Science and Technology Austria.","ieee":"A. Zimin, “Learning from dependent data,” Institute of Science and Technology Austria, 2018.","short":"A. Zimin, Learning from Dependent Data, Institute of Science and Technology Austria, 2018.","mla":"Zimin, Alexander. <i>Learning from Dependent Data</i>. Institute of Science and Technology Austria, 2018, doi:<a href=\"https://doi.org/10.15479/AT:ISTA:TH1048\">10.15479/AT:ISTA:TH1048</a>.","chicago":"Zimin, Alexander. “Learning from Dependent Data.” Institute of Science and Technology Austria, 2018. <a href=\"https://doi.org/10.15479/AT:ISTA:TH1048\">https://doi.org/10.15479/AT:ISTA:TH1048</a>.","ama":"Zimin A. Learning from dependent data. 2018. doi:<a href=\"https://doi.org/10.15479/AT:ISTA:TH1048\">10.15479/AT:ISTA:TH1048</a>","apa":"Zimin, A. (2018). <i>Learning from dependent data</i>. Institute of Science and Technology Austria. <a href=\"https://doi.org/10.15479/AT:ISTA:TH1048\">https://doi.org/10.15479/AT:ISTA:TH1048</a>"},"supervisor":[{"first_name":"Christoph","orcid":"0000-0001-8622-7887","last_name":"Lampert","full_name":"Lampert, Christoph","id":"40C20FD2-F248-11E8-B48F-1D18A9856A87"}],"user_id":"ba8df636-2132-11f1-aed0-ed93e2281fdd","doi":"10.15479/AT:ISTA:TH1048","date_created":"2018-12-11T11:44:27Z","author":[{"first_name":"Alexander","last_name":"Zimin","full_name":"Zimin, Alexander","id":"37099E9C-F248-11E8-B48F-1D18A9856A87"}],"_id":"68","OA_place":"publisher","file":[{"file_name":"2018_Thesis_Zimin.pdf","checksum":"e849dd40a915e4d6c5572b51b517f098","date_created":"2019-04-09T07:32:47Z","file_id":"6253","access_level":"open_access","creator":"dernst","relation":"main_file","file_size":1036137,"date_updated":"2020-07-14T12:47:40Z","content_type":"application/pdf"},{"creator":"dernst","access_level":"closed","file_id":"6254","file_name":"2018_Thesis_Zimin_Source.zip","date_created":"2019-04-09T07:32:47Z","checksum":"da092153cec55c97461bd53c45c5d139","relation":"source_file","file_size":637490,"date_updated":"2020-07-14T12:47:40Z","content_type":"application/zip"}],"ddc":["004","519"],"date_updated":"2026-04-08T14:05:50Z","language":[{"iso":"eng"}],"article_processing_charge":"No","department":[{"_id":"ChLa"}],"has_accepted_license":"1","status":"public","type":"dissertation","project":[{"_id":"2532554C-B435-11E9-9278-68D0E5697425","call_identifier":"FP7","name":"Lifelong Learning of Visual Scene Understanding","grant_number":"308036"}],"pubrep_id":"1048","year":"2018","ec_funded":1,"degree_awarded":"PhD","publist_id":"7986","day":"01","publisher":"Institute of Science and Technology Austria","corr_author":"1","month":"09"}]