[{"author":[{"id":"f9a17499-f6e0-11ea-865d-fdf9a3f77117","full_name":"Iofinova, Eugenia B","orcid":"0000-0002-7778-3221","last_name":"Iofinova","first_name":"Eugenia B"},{"full_name":"Peste, Elena-Alexandra","id":"32D78294-F248-11E8-B48F-1D18A9856A87","first_name":"Elena-Alexandra","last_name":"Peste"},{"last_name":"Alistarh","first_name":"Dan-Adrian","id":"4A899BFC-F248-11E8-B48F-1D18A9856A87","full_name":"Alistarh, Dan-Adrian","orcid":"0000-0003-3650-940X"}],"publication_status":"published","external_id":{"isi":["001062531308068"],"arxiv":["2304.12622"]},"corr_author":"1","project":[{"_id":"9B9290DE-BA93-11EA-9121-9846C619BF3A","grant_number":"W1260-N35","name":"Vienna Graduate School on Computational Optimization"},{"_id":"268A44D6-B435-11E9-9278-68D0E5697425","grant_number":"805223","call_identifier":"H2020","name":"Elastic Coordination for Scalable Machine Learning"}],"month":"08","abstract":[{"lang":"eng","text":"Pruning—that is, setting a significant subset of the parameters of a neural network to zero—is one of the most popular methods of model compression. Yet, several recent works have raised the issue that pruning may induce or exacerbate bias in the output of the compressed model. Despite existing evidence for this phenomenon, the relationship between neural network pruning and induced bias is not well-understood. In this work, we systematically investigate and characterize this phenomenon in Convolutional Neural Networks for computer vision. First, we show that it is in fact possible to obtain highly-sparse models, e.g. with less than 10% remaining weights, which do not decrease in accuracy nor substantially increase in bias when compared to dense models. At the same time, we also find that, at higher sparsities, pruned models exhibit higher uncertainty in their outputs, as well as increased correlations, which we directly link to increased bias. We propose easy-to-use criteria which, based only on the uncompressed model, establish whether bias will increase with pruning, and identify the samples most susceptible to biased predictions post-compression. Our code can be found at https://github.com/IST-DASLab/pruned-vision-model-bias."}],"language":[{"iso":"eng"}],"acknowledgement":"The authors would like to sincerely thank Sara Hooker for her feedback during the development of this work. EI was supported in part by the FWF DK VGSCO, grant agreement number W1260-N35. AP and DA acknowledge generous ERC support, via Starting Grant 805223 ScaleML.","oa":1,"isi":1,"date_created":"2024-01-10T08:42:40Z","date_published":"2023-08-22T00:00:00Z","year":"2023","article_processing_charge":"No","arxiv":1,"type":"conference","ec_funded":1,"status":"public","doi":"10.1109/cvpr52729.2023.02334","publication_identifier":{"eisbn":["9798350301298"],"eissn":["2575-7075"]},"quality_controlled":"1","conference":{"end_date":"2023-06-24","name":"CVPR: Conference on Computer Vision and Pattern Recognition","start_date":"2023-06-17","location":"Vancouver, BC, Canada"},"user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","oa_version":"Preprint","related_material":{"link":[{"relation":"software","url":"https://github.com/IST-DASLab/pruned-vision-model-bias"}],"record":[{"status":"public","id":"21854","relation":"dissertation_contains"}]},"page":"24364-24373","date_updated":"2026-05-19T11:20:27Z","day":"22","main_file_link":[{"url":"https://doi.org/10.48550/arXiv.2304.12622","open_access":"1"}],"publisher":"IEEE","department":[{"_id":"DaAl"},{"_id":"ChLa"}],"publication":"2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition","citation":{"ista":"Iofinova EB, Krumes A, Alistarh D-A. 2023. Bias in pruned vision models: In-depth analysis and countermeasures. 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition. CVPR: Conference on Computer Vision and Pattern Recognition, 24364–24373.","chicago":"Iofinova, Eugenia B, Alexandra Krumes, and Dan-Adrian Alistarh. “Bias in Pruned Vision Models: In-Depth Analysis and Countermeasures.” In <i>2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition</i>, 24364–73. IEEE, 2023. <a href=\"https://doi.org/10.1109/cvpr52729.2023.02334\">https://doi.org/10.1109/cvpr52729.2023.02334</a>.","short":"E.B. Iofinova, A. Krumes, D.-A. Alistarh, in:, 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, IEEE, 2023, pp. 24364–24373.","apa":"Iofinova, E. B., Krumes, A., &#38; Alistarh, D.-A. (2023). Bias in pruned vision models: In-depth analysis and countermeasures. In <i>2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition</i> (pp. 24364–24373). Vancouver, BC, Canada: IEEE. <a href=\"https://doi.org/10.1109/cvpr52729.2023.02334\">https://doi.org/10.1109/cvpr52729.2023.02334</a>","mla":"Iofinova, Eugenia B., et al. “Bias in Pruned Vision Models: In-Depth Analysis and Countermeasures.” <i>2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition</i>, IEEE, 2023, pp. 24364–73, doi:<a href=\"https://doi.org/10.1109/cvpr52729.2023.02334\">10.1109/cvpr52729.2023.02334</a>.","ieee":"E. B. Iofinova, A. Krumes, and D.-A. Alistarh, “Bias in pruned vision models: In-depth analysis and countermeasures,” in <i>2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition</i>, Vancouver, BC, Canada, 2023, pp. 24364–24373.","ama":"Iofinova EB, Krumes A, Alistarh D-A. Bias in pruned vision models: In-depth analysis and countermeasures. In: <i>2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition</i>. IEEE; 2023:24364-24373. doi:<a href=\"https://doi.org/10.1109/cvpr52729.2023.02334\">10.1109/cvpr52729.2023.02334</a>"},"title":"Bias in pruned vision models: In-depth analysis and countermeasures","_id":"14771"},{"ec_funded":1,"status":"public","publication_identifier":{"eissn":["2575-7075"]},"doi":"10.1109/cvpr52688.2022.01195","quality_controlled":"1","conference":{"name":"CVPR: Computer Vision and Pattern Recognition","start_date":"2022-06-18","location":"New Orleans, LA, United States","end_date":"2022-06-24"},"user_id":"4359f0d1-fa6c-11eb-b949-802e58b17ae8","scopus_import":"1","oa_version":"Preprint","page":"12256-12266","related_material":{"record":[{"id":"13074","relation":"dissertation_contains","status":"public"}]},"article_processing_charge":"No","arxiv":1,"type":"conference","main_file_link":[{"url":"https://doi.org/10.48550/arXiv.2111.13445","open_access":"1"}],"publisher":"Institute of Electrical and Electronics Engineers","department":[{"_id":"DaAl"},{"_id":"ChLa"}],"publication":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition","citation":{"ama":"Iofinova EB, Krumes A, Kurtz M, Alistarh D-A. How well do sparse ImageNet models transfer? In: <i>2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition</i>. Institute of Electrical and Electronics Engineers; 2022:12256-12266. doi:<a href=\"https://doi.org/10.1109/cvpr52688.2022.01195\">10.1109/cvpr52688.2022.01195</a>","apa":"Iofinova, E. B., Krumes, A., Kurtz, M., &#38; Alistarh, D.-A. (2022). How well do sparse ImageNet models transfer? In <i>2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition</i> (pp. 12256–12266). New Orleans, LA, United States: Institute of Electrical and Electronics Engineers. <a href=\"https://doi.org/10.1109/cvpr52688.2022.01195\">https://doi.org/10.1109/cvpr52688.2022.01195</a>","mla":"Iofinova, Eugenia B., et al. “How Well Do Sparse ImageNet Models Transfer?” <i>2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition</i>, Institute of Electrical and Electronics Engineers, 2022, pp. 12256–66, doi:<a href=\"https://doi.org/10.1109/cvpr52688.2022.01195\">10.1109/cvpr52688.2022.01195</a>.","ieee":"E. B. Iofinova, A. Krumes, M. Kurtz, and D.-A. Alistarh, “How well do sparse ImageNet models transfer?,” in <i>2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition</i>, New Orleans, LA, United States, 2022, pp. 12256–12266.","short":"E.B. Iofinova, A. Krumes, M. Kurtz, D.-A. Alistarh, in:, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Institute of Electrical and Electronics Engineers, 2022, pp. 12256–12266.","ista":"Iofinova EB, Krumes A, Kurtz M, Alistarh D-A. 2022. How well do sparse ImageNet models transfer? 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. CVPR: Computer Vision and Pattern Recognition, 12256–12266.","chicago":"Iofinova, Eugenia B, Alexandra Krumes, Mark Kurtz, and Dan-Adrian Alistarh. “How Well Do Sparse ImageNet Models Transfer?” In <i>2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition</i>, 12256–66. Institute of Electrical and Electronics Engineers, 2022. <a href=\"https://doi.org/10.1109/cvpr52688.2022.01195\">https://doi.org/10.1109/cvpr52688.2022.01195</a>."},"title":"How well do sparse ImageNet models transfer?","_id":"12299","date_updated":"2026-04-07T13:30:19Z","day":"27","project":[{"_id":"9B9290DE-BA93-11EA-9121-9846C619BF3A","grant_number":"W1260-N35","name":"Vienna Graduate School on Computational Optimization"},{"name":"Elastic Coordination for Scalable Machine Learning","call_identifier":"H2020","grant_number":"805223","_id":"268A44D6-B435-11E9-9278-68D0E5697425"}],"author":[{"first_name":"Eugenia B","last_name":"Iofinova","orcid":"0000-0002-7778-3221","full_name":"Iofinova, Eugenia B","id":"f9a17499-f6e0-11ea-865d-fdf9a3f77117"},{"first_name":"Elena-Alexandra","last_name":"Peste","full_name":"Peste, Elena-Alexandra","id":"32D78294-F248-11E8-B48F-1D18A9856A87"},{"full_name":"Kurtz, Mark","last_name":"Kurtz","first_name":"Mark"},{"orcid":"0000-0003-3650-940X","full_name":"Alistarh, Dan-Adrian","id":"4A899BFC-F248-11E8-B48F-1D18A9856A87","first_name":"Dan-Adrian","last_name":"Alistarh"}],"publication_status":"published","external_id":{"arxiv":["2111.13445"],"isi":["000870759105034"]},"corr_author":"1","acknowledgement":"he authors would like to sincerely thank Christoph Lampert and Nir Shavit for fruitful discussions during the development of this work, and Eldar Kurtic for experimental support. EI was supported in part by the FWF DK VGSCO, grant agreement number W1260-N35, while AP and DA acknowledge generous support by the ERC, via Starting Grant 805223 ScaleML.","language":[{"iso":"eng"}],"oa":1,"isi":1,"date_created":"2023-01-16T10:06:00Z","date_published":"2022-09-27T00:00:00Z","year":"2022","month":"09","abstract":[{"text":"Transfer learning is a classic paradigm by which models pretrained on large “upstream” datasets are adapted to yield good results on “downstream” specialized datasets. Generally, more accurate models on the “upstream” dataset tend to provide better transfer accuracy “downstream”. In this work, we perform an in-depth investigation of this phenomenon in the context of convolutional neural networks (CNNs) trained on the ImageNet dataset, which have been pruned-that is, compressed by sparsifiying their connections. We consider transfer using unstructured pruned models obtained by applying several state-of-the-art pruning methods, including magnitude-based, second-order, regrowth, lottery-ticket, and regularization approaches, in the context of twelve standard transfer tasks. In a nutshell, our study shows that sparse models can match or even outperform the transfer performance of dense models, even at high sparsities, and, while doing so, can lead to significant inference and even training speedups. At the same time, we observe and analyze significant differences in the behaviour of different pruning methods. The code is available at: https://github.com/IST-DASLab/sparse-imagenet-transfer.","lang":"eng"}]},{"doi":"10.1109/cvpr52688.2022.01016","publication_identifier":{"eissn":["2575-7075"],"isbn":["9781665469470"],"issn":["1063-6919"]},"quality_controlled":"1","status":"public","scopus_import":"1","oa_version":"Preprint","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","page":"10400-10411","conference":{"name":"CVPR: Conference on Computer Vision and Pattern Recognition","start_date":"2022-06-18","location":"New Orleans, LA, United States","end_date":"2022-06-24"},"extern":"1","type":"conference","article_processing_charge":"No","arxiv":1,"publication":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition","citation":{"ama":"Zietlow D, Lohaus M, Balakrishnan G, et al. Leveling down in computer vision: Pareto inefficiencies in fair deep classifiers. In: <i>2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition</i>. Institute of Electrical and Electronics Engineers; 2022:10400-10411. doi:<a href=\"https://doi.org/10.1109/cvpr52688.2022.01016\">10.1109/cvpr52688.2022.01016</a>","ieee":"D. Zietlow <i>et al.</i>, “Leveling down in computer vision: Pareto inefficiencies in fair deep classifiers,” in <i>2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition</i>, New Orleans, LA, United States, 2022, pp. 10400–10411.","mla":"Zietlow, Dominik, et al. “Leveling down in Computer Vision: Pareto Inefficiencies in Fair Deep Classifiers.” <i>2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition</i>, Institute of Electrical and Electronics Engineers, 2022, pp. 10400–11, doi:<a href=\"https://doi.org/10.1109/cvpr52688.2022.01016\">10.1109/cvpr52688.2022.01016</a>.","apa":"Zietlow, D., Lohaus, M., Balakrishnan, G., Kleindessner, M., Locatello, F., Scholkopf, B., &#38; Russell, C. (2022). Leveling down in computer vision: Pareto inefficiencies in fair deep classifiers. In <i>2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition</i> (pp. 10400–10411). New Orleans, LA, United States: Institute of Electrical and Electronics Engineers. <a href=\"https://doi.org/10.1109/cvpr52688.2022.01016\">https://doi.org/10.1109/cvpr52688.2022.01016</a>","short":"D. Zietlow, M. Lohaus, G. Balakrishnan, M. Kleindessner, F. Locatello, B. Scholkopf, C. Russell, in:, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Institute of Electrical and Electronics Engineers, 2022, pp. 10400–10411.","chicago":"Zietlow, Dominik, Michael Lohaus, Guha Balakrishnan, Matthaus Kleindessner, Francesco Locatello, Bernhard Scholkopf, and Chris Russell. “Leveling down in Computer Vision: Pareto Inefficiencies in Fair Deep Classifiers.” In <i>2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition</i>, 10400–411. Institute of Electrical and Electronics Engineers, 2022. <a href=\"https://doi.org/10.1109/cvpr52688.2022.01016\">https://doi.org/10.1109/cvpr52688.2022.01016</a>.","ista":"Zietlow D, Lohaus M, Balakrishnan G, Kleindessner M, Locatello F, Scholkopf B, Russell C. 2022. Leveling down in computer vision: Pareto inefficiencies in fair deep classifiers. 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. CVPR: Conference on Computer Vision and Pattern Recognition, 10400–10411."},"main_file_link":[{"url":"https://arxiv.org/abs/2203.04913","open_access":"1"}],"publisher":"Institute of Electrical and Electronics Engineers","department":[{"_id":"FrLo"}],"_id":"14114","title":"Leveling down in computer vision: Pareto inefficiencies in fair deep classifiers","date_updated":"2023-09-11T09:19:14Z","day":"01","author":[{"last_name":"Zietlow","first_name":"Dominik","full_name":"Zietlow, Dominik"},{"full_name":"Lohaus, Michael","first_name":"Michael","last_name":"Lohaus"},{"last_name":"Balakrishnan","first_name":"Guha","full_name":"Balakrishnan, Guha"},{"first_name":"Matthaus","last_name":"Kleindessner","full_name":"Kleindessner, Matthaus"},{"last_name":"Locatello","first_name":"Francesco","id":"26cfd52f-2483-11ee-8040-88983bcc06d4","full_name":"Locatello, Francesco","orcid":"0000-0002-4850-0683"},{"last_name":"Scholkopf","first_name":"Bernhard","full_name":"Scholkopf, Bernhard"},{"last_name":"Russell","first_name":"Chris","full_name":"Russell, Chris"}],"external_id":{"arxiv":["2203.04913"]},"publication_status":"published","language":[{"iso":"eng"}],"oa":1,"date_published":"2022-07-01T00:00:00Z","year":"2022","date_created":"2023-08-21T12:18:00Z","abstract":[{"lang":"eng","text":"Algorithmic fairness is frequently motivated in terms of a trade-off in which overall performance is decreased so as to improve performance on disadvantaged groups where the algorithm would otherwise be less accurate. Contrary to this, we find that applying existing fairness approaches to computer vision improve fairness by degrading the performance of classifiers across all groups (with increased degradation on the best performing groups). Extending the bias-variance decomposition for classification to fairness, we theoretically explain why the majority of fairness methods designed for low capacity models should not be used in settings involving high-capacity models, a scenario common to computer vision. We corroborate this analysis with extensive experimental support that shows that many of the fairness heuristics used in computer vision also degrade performance on the most disadvantaged groups. Building on these insights, we propose an adaptive augmentation strategy that, uniquely, of all methods tested, improves performance for the disadvantaged groups."}],"month":"07"},{"publisher":"IEEE","publication":"2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","citation":{"short":"L. Karlinsky, J. Shtok, S. Harary, E. Schwartz, A. Aides, R. Feris, R. Giryes, A.M. Bronstein, in:, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, 2020.","chicago":"Karlinsky, Leonid, Joseph Shtok, Sivan Harary, Eli Schwartz, Amit Aides, Rogerio Feris, Raja Giryes, and Alex M. Bronstein. “Repmet: Representative-Based Metric Learning for Classification and Few-Shot Object Detection.” In <i>2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)</i>. IEEE, 2020. <a href=\"https://doi.org/10.1109/cvpr.2019.00534\">https://doi.org/10.1109/cvpr.2019.00534</a>.","ista":"Karlinsky L, Shtok J, Harary S, Schwartz E, Aides A, Feris R, Giryes R, Bronstein AM. 2020. Repmet: Representative-based metric learning for classification and few-shot object detection. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition, 8953439.","ama":"Karlinsky L, Shtok J, Harary S, et al. Repmet: Representative-based metric learning for classification and few-shot object detection. In: <i>2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)</i>. IEEE; 2020. doi:<a href=\"https://doi.org/10.1109/cvpr.2019.00534\">10.1109/cvpr.2019.00534</a>","ieee":"L. Karlinsky <i>et al.</i>, “Repmet: Representative-based metric learning for classification and few-shot object detection,” in <i>2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)</i>, Long Beach, CA, United States, 2020.","mla":"Karlinsky, Leonid, et al. “Repmet: Representative-Based Metric Learning for Classification and Few-Shot Object Detection.” <i>2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)</i>, 8953439, IEEE, 2020, doi:<a href=\"https://doi.org/10.1109/cvpr.2019.00534\">10.1109/cvpr.2019.00534</a>.","apa":"Karlinsky, L., Shtok, J., Harary, S., Schwartz, E., Aides, A., Feris, R., … Bronstein, A. M. (2020). Repmet: Representative-based metric learning for classification and few-shot object detection. In <i>2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)</i>. Long Beach, CA, United States: IEEE. <a href=\"https://doi.org/10.1109/cvpr.2019.00534\">https://doi.org/10.1109/cvpr.2019.00534</a>"},"language":[{"iso":"eng"}],"date_created":"2024-10-08T13:08:09Z","_id":"18258","title":"Repmet: Representative-based metric learning for classification and few-shot object detection","date_published":"2020-01-09T00:00:00Z","year":"2020","date_updated":"2024-12-05T15:38:16Z","month":"01","day":"09","abstract":[{"text":"Distance metric learning (DML) has been successfully applied to object classification, both in the standard regime of rich training data and in the few-shot scenario, where each category is represented by only a few examples. In this work, we propose a new method for DML that simultaneously learns the backbone network parameters, the embedding space, and the multi-modal distribution of each of the training categories in that space, in a single end-to-end training process. Our approach outperforms state-of-the-art methods for DML-based object classification on a variety of standard fine-grained datasets. Furthermore, we demonstrate the effectiveness of our approach on the problem of few-shot object detection, by incorporating the proposed DML architecture as a classification head into a standard object detection model. We achieve the best results on the ImageNet-LOC dataset compared to strong baselines, when only a few training examples are available. We also offer the community a new episodic benchmark based on the ImageNet dataset for the few-shot object detection task.","lang":"eng"}],"status":"public","publication_identifier":{"eissn":["2575-7075"],"isbn":["9781728132945"]},"doi":"10.1109/cvpr.2019.00534","quality_controlled":"1","conference":{"end_date":"2019-06-20","location":"Long Beach, CA, United States","start_date":"2019-06-15","name":"32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition"},"user_id":"3E5EF7F0-F248-11E8-B48F-1D18A9856A87","scopus_import":"1","oa_version":"None","author":[{"first_name":"Leonid","last_name":"Karlinsky","full_name":"Karlinsky, Leonid"},{"full_name":"Shtok, Joseph","first_name":"Joseph","last_name":"Shtok"},{"full_name":"Harary, Sivan","first_name":"Sivan","last_name":"Harary"},{"full_name":"Schwartz, Eli","first_name":"Eli","last_name":"Schwartz"},{"full_name":"Aides, Amit","last_name":"Aides","first_name":"Amit"},{"first_name":"Rogerio","last_name":"Feris","full_name":"Feris, Rogerio"},{"last_name":"Giryes","first_name":"Raja","full_name":"Giryes, Raja"},{"first_name":"Alexander","last_name":"Bronstein","full_name":"Bronstein, Alexander","orcid":"0000-0001-9699-8730","id":"58f3726e-7cba-11ef-ad8b-e6e8cb3904e6"}],"publication_status":"published","article_number":"8953439","article_processing_charge":"No","extern":"1","type":"conference"},{"date_created":"2024-10-08T13:08:26Z","year":"2020","date_published":"2020-01-09T00:00:00Z","oa":1,"language":[{"iso":"eng"}],"month":"01","abstract":[{"text":"Example synthesis is one of the leading methods to tackle the problem of few-shot learning, where only a small number of samples per class are available. However, current synthesis approaches only address the scenario of a single category label per image. In this work, we propose a novel technique for synthesizing samples with multiple labels for the (yet unhandled) multi-label few-shot classification scenario. We propose to combine pairs of given examples in feature space, so that the resulting synthesized feature vectors will correspond to examples whose label sets are obtained through certain set operations on the label sets of the corresponding input pairs. Thus, our method is capable of producing a sample containing the intersection, union or set-difference of labels present in two input samples. As we show, these set operations generalize to labels unseen during training. This enables performing augmentation on examples of novel categories, thus, facilitating multi-label few-shot classifier learning. We conduct numerous experiments showing promising results for the label-set manipulation capabilities of the proposed approach, both directly (using the classification and retrieval metrics), and in the context of performing data augmentation for multi-label few-shot learning. We propose a benchmark for this new and challenging task and show that our method compares favorably to all the common baselines.","lang":"eng"}],"article_number":"8954088","publication_status":"published","external_id":{"arxiv":["1902.09811"]},"author":[{"first_name":"Amit","last_name":"Alfassy","full_name":"Alfassy, Amit"},{"full_name":"Karlinsky, Leonid","first_name":"Leonid","last_name":"Karlinsky"},{"full_name":"Aides, Amit","first_name":"Amit","last_name":"Aides"},{"full_name":"Shtok, Joseph","first_name":"Joseph","last_name":"Shtok"},{"full_name":"Harary, Sivan","first_name":"Sivan","last_name":"Harary"},{"full_name":"Feris, Rogerio","first_name":"Rogerio","last_name":"Feris"},{"full_name":"Giryes, Raja","first_name":"Raja","last_name":"Giryes"},{"id":"58f3726e-7cba-11ef-ad8b-e6e8cb3904e6","full_name":"Bronstein, Alexander","orcid":"0000-0001-9699-8730","last_name":"Bronstein","first_name":"Alexander"}],"title":"Laso: Label-set operations networks for multi-label few-shot learning","_id":"18259","publisher":"IEEE","main_file_link":[{"url":"https://doi.org/10.48550/arXiv.1902.09811","open_access":"1"}],"citation":{"short":"A. Alfassy, L. Karlinsky, A. Aides, J. Shtok, S. Harary, R. Feris, R. Giryes, A.M. Bronstein, in:, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, 2020.","chicago":"Alfassy, Amit, Leonid Karlinsky, Amit Aides, Joseph Shtok, Sivan Harary, Rogerio Feris, Raja Giryes, and Alex M. Bronstein. “Laso: Label-Set Operations Networks for Multi-Label Few-Shot Learning.” In <i>2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)</i>. IEEE, 2020. <a href=\"https://doi.org/10.1109/cvpr.2019.00671\">https://doi.org/10.1109/cvpr.2019.00671</a>.","ista":"Alfassy A, Karlinsky L, Aides A, Shtok J, Harary S, Feris R, Giryes R, Bronstein AM. 2020. Laso: Label-set operations networks for multi-label few-shot learning. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition, 8954088.","ama":"Alfassy A, Karlinsky L, Aides A, et al. Laso: Label-set operations networks for multi-label few-shot learning. In: <i>2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)</i>. IEEE; 2020. doi:<a href=\"https://doi.org/10.1109/cvpr.2019.00671\">10.1109/cvpr.2019.00671</a>","ieee":"A. Alfassy <i>et al.</i>, “Laso: Label-set operations networks for multi-label few-shot learning,” in <i>2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)</i>, Long Beach, CA, United States, 2020.","apa":"Alfassy, A., Karlinsky, L., Aides, A., Shtok, J., Harary, S., Feris, R., … Bronstein, A. M. (2020). Laso: Label-set operations networks for multi-label few-shot learning. In <i>2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)</i>. Long Beach, CA, United States: IEEE. <a href=\"https://doi.org/10.1109/cvpr.2019.00671\">https://doi.org/10.1109/cvpr.2019.00671</a>","mla":"Alfassy, Amit, et al. “Laso: Label-Set Operations Networks for Multi-Label Few-Shot Learning.” <i>2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)</i>, 8954088, IEEE, 2020, doi:<a href=\"https://doi.org/10.1109/cvpr.2019.00671\">10.1109/cvpr.2019.00671</a>."},"publication":"2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","day":"09","date_updated":"2024-12-05T15:33:21Z","conference":{"start_date":"2019-06-15","name":"32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition","location":"Long Beach, CA, United States","end_date":"2019-06-20"},"oa_version":"Preprint","scopus_import":"1","user_id":"3E5EF7F0-F248-11E8-B48F-1D18A9856A87","status":"public","quality_controlled":"1","doi":"10.1109/cvpr.2019.00671","publication_identifier":{"isbn":["9781728132945"],"eissn":["2575-7075"]},"arxiv":1,"article_processing_charge":"No","extern":"1","type":"conference"},{"publisher":"IEEE","language":[{"iso":"eng"}],"citation":{"ama":"Halimi O, Litany O, Rodola ER, Bronstein AM, Kimmel R. Unsupervised learning of dense shape correspondence. In: <i>2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)</i>. IEEE; 2020. doi:<a href=\"https://doi.org/10.1109/cvpr.2019.00450\">10.1109/cvpr.2019.00450</a>","ieee":"O. Halimi, O. Litany, E. R. Rodola, A. M. Bronstein, and R. Kimmel, “Unsupervised learning of dense shape correspondence,” in <i>2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)</i>, Long Beach, CA, United States, 2020.","mla":"Halimi, Oshri, et al. “Unsupervised Learning of Dense Shape Correspondence.” <i>2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)</i>, 8953366, IEEE, 2020, doi:<a href=\"https://doi.org/10.1109/cvpr.2019.00450\">10.1109/cvpr.2019.00450</a>.","apa":"Halimi, O., Litany, O., Rodola, E. R., Bronstein, A. M., &#38; Kimmel, R. (2020). Unsupervised learning of dense shape correspondence. In <i>2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)</i>. Long Beach, CA, United States: IEEE. <a href=\"https://doi.org/10.1109/cvpr.2019.00450\">https://doi.org/10.1109/cvpr.2019.00450</a>","short":"O. Halimi, O. Litany, E.R. Rodola, A.M. Bronstein, R. Kimmel, in:, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, 2020.","chicago":"Halimi, Oshri, Or Litany, Emanuele Rodola Rodola, Alex M. Bronstein, and Ron Kimmel. “Unsupervised Learning of Dense Shape Correspondence.” In <i>2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)</i>. IEEE, 2020. <a href=\"https://doi.org/10.1109/cvpr.2019.00450\">https://doi.org/10.1109/cvpr.2019.00450</a>.","ista":"Halimi O, Litany O, Rodola ER, Bronstein AM, Kimmel R. 2020. Unsupervised learning of dense shape correspondence. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition, 8953366."},"publication":"2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","_id":"18260","title":"Unsupervised learning of dense shape correspondence","date_created":"2024-10-08T13:08:43Z","year":"2020","date_published":"2020-01-09T00:00:00Z","date_updated":"2024-12-05T15:19:01Z","month":"01","day":"09","abstract":[{"text":"We introduce the first completely unsupervised correspondence learning approach for deformable 3D shapes. Key to our model is the understanding that natural deformations (such as changes in pose) approximately preserve the metric structure of the surface, yielding a natural criterion to drive the learning process toward distortion-minimizing predictions. On this basis, we overcome the need for annotated data and replace it by a purely geometric criterion. The resulting learning model is class-agnostic, and is able to leverage any type of deformable geometric data for the training phase. In contrast to existing supervised approaches which specialize on the class seen at training time, we demonstrate stronger generalization as well as applicability to a variety of challenging settings. We showcase our method on a wide selection of correspondence benchmarks, where we outperform other methods in terms of accuracy, generalization, and efficiency.","lang":"eng"}],"status":"public","quality_controlled":"1","publication_identifier":{"isbn":["9781728132945"],"eissn":["2575-7075"]},"doi":"10.1109/cvpr.2019.00450","conference":{"end_date":"2019-06-20","location":"Long Beach, CA, United States","name":"32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition","start_date":"2019-06-15"},"oa_version":"None","user_id":"3E5EF7F0-F248-11E8-B48F-1D18A9856A87","scopus_import":"1","author":[{"full_name":"Halimi, Oshri","first_name":"Oshri","last_name":"Halimi"},{"full_name":"Litany, Or","first_name":"Or","last_name":"Litany"},{"last_name":"Rodola","first_name":"Emanuele Rodola","full_name":"Rodola, Emanuele Rodola"},{"first_name":"Alexander","last_name":"Bronstein","full_name":"Bronstein, Alexander","orcid":"0000-0001-9699-8730","id":"58f3726e-7cba-11ef-ad8b-e6e8cb3904e6"},{"first_name":"Ron","last_name":"Kimmel","full_name":"Kimmel, Ron"}],"article_number":"8953366","article_processing_charge":"No","publication_status":"published","type":"conference","extern":"1"},{"title":"Leveraging 2D data to learn textured 3D mesh generation","_id":"8186","citation":{"chicago":"Henderson, Paul M, Vagia Tsiminaki, and Christoph Lampert. “Leveraging 2D Data to Learn Textured 3D Mesh Generation.” In <i>Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition</i>, 7498–7507. IEEE, 2020. <a href=\"https://doi.org/10.1109/CVPR42600.2020.00752\">https://doi.org/10.1109/CVPR42600.2020.00752</a>.","ista":"Henderson PM, Tsiminaki V, Lampert C. 2020. Leveraging 2D data to learn textured 3D mesh generation. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. CVPR: Conference on Computer Vision and Pattern Recognition, 7498–7507.","short":"P.M. Henderson, V. Tsiminaki, C. Lampert, in:, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, IEEE, 2020, pp. 7498–7507.","ieee":"P. M. Henderson, V. Tsiminaki, and C. Lampert, “Leveraging 2D data to learn textured 3D mesh generation,” in <i>Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition</i>, Virtual, 2020, pp. 7498–7507.","mla":"Henderson, Paul M., et al. “Leveraging 2D Data to Learn Textured 3D Mesh Generation.” <i>Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition</i>, IEEE, 2020, pp. 7498–507, doi:<a href=\"https://doi.org/10.1109/CVPR42600.2020.00752\">10.1109/CVPR42600.2020.00752</a>.","apa":"Henderson, P. M., Tsiminaki, V., &#38; Lampert, C. (2020). Leveraging 2D data to learn textured 3D mesh generation. In <i>Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition</i> (pp. 7498–7507). Virtual: IEEE. <a href=\"https://doi.org/10.1109/CVPR42600.2020.00752\">https://doi.org/10.1109/CVPR42600.2020.00752</a>","ama":"Henderson PM, Tsiminaki V, Lampert C. Leveraging 2D data to learn textured 3D mesh generation. In: <i>Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition</i>. IEEE; 2020:7498-7507. doi:<a href=\"https://doi.org/10.1109/CVPR42600.2020.00752\">10.1109/CVPR42600.2020.00752</a>"},"has_accepted_license":"1","publication":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition","department":[{"_id":"ChLa"}],"publisher":"IEEE","file":[{"access_level":"open_access","date_created":"2020-07-31T16:57:12Z","relation":"main_file","content_type":"application/pdf","file_size":10262773,"creator":"phenders","file_id":"8187","success":1,"date_updated":"2020-07-31T16:57:12Z","file_name":"paper.pdf"}],"main_file_link":[{"url":"https://openaccess.thecvf.com/content_CVPR_2020/papers/Henderson_Leveraging_2D_Data_to_Learn_Textured_3D_Mesh_Generation_CVPR_2020_paper.pdf","open_access":"1"}],"day":"01","date_updated":"2023-10-17T07:37:11Z","page":"7498-7507","oa_version":"Submitted Version","scopus_import":"1","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","conference":{"start_date":"2020-06-14","name":"CVPR: Conference on Computer Vision and Pattern Recognition","location":"Virtual","end_date":"2020-06-19"},"quality_controlled":"1","doi":"10.1109/CVPR42600.2020.00752","publication_identifier":{"eissn":["2575-7075"],"eisbn":["9781728171685"]},"status":"public","type":"conference","arxiv":1,"article_processing_charge":"No","ddc":["004"],"year":"2020","file_date_updated":"2020-07-31T16:57:12Z","date_published":"2020-07-01T00:00:00Z","date_created":"2020-07-31T16:53:49Z","language":[{"iso":"eng"}],"oa":1,"abstract":[{"text":"Numerous methods have been proposed for probabilistic generative modelling of\r\n3D objects. However, none of these is able to produce textured objects, which\r\nrenders them of limited use for practical tasks. In this work, we present the\r\nfirst generative model of textured 3D meshes. Training such a model would\r\ntraditionally require a large dataset of textured meshes, but unfortunately,\r\nexisting datasets of meshes lack detailed textures. We instead propose a new\r\ntraining methodology that allows learning from collections of 2D images without\r\nany 3D information. To do so, we train our model to explain a distribution of\r\nimages by modelling each image as a 3D foreground object placed in front of a\r\n2D background. Thus, it learns to generate meshes that when rendered, produce\r\nimages similar to those in its training set.\r\n  A well-known problem when generating meshes with deep networks is the\r\nemergence of self-intersections, which are problematic for many use-cases. As a\r\nsecond contribution we therefore introduce a new generation process for 3D\r\nmeshes that guarantees no self-intersections arise, based on the physical\r\nintuition that faces should push one another out of the way as they move.\r\n  We conduct extensive experiments on our approach, reporting quantitative and\r\nqualitative results on both synthetic data and natural images. These show our\r\nmethod successfully learns to generate plausible and diverse textured 3D\r\nsamples for five challenging object classes.","lang":"eng"}],"month":"07","external_id":{"arxiv":["2004.04180"]},"publication_status":"published","author":[{"id":"13C09E74-18D9-11E9-8878-32CFE5697425","orcid":"0000-0002-5198-7445","full_name":"Henderson, Paul M","last_name":"Henderson","first_name":"Paul M"},{"last_name":"Tsiminaki","first_name":"Vagia","full_name":"Tsiminaki, Vagia"},{"first_name":"Christoph","last_name":"Lampert","orcid":"0000-0001-8622-7887","full_name":"Lampert, Christoph","id":"40C20FD2-F248-11E8-B48F-1D18A9856A87"}]},{"title":"Learning intelligent dialogs for bounding box annotation","_id":"10882","publication":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition","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>.","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.","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>","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.","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>.","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>"},"main_file_link":[{"open_access":"1","url":" https://doi.org/10.48550/arXiv.1712.08087"}],"publisher":"IEEE","department":[{"_id":"ChLa"}],"day":"17","date_updated":"2024-10-09T21:02:26Z","user_id":"c635000d-4b10-11ee-a964-aac5a93f6ac1","oa_version":"Preprint","scopus_import":"1","page":"9175-9184","conference":{"end_date":"2018-06-23","location":"Salt Lake City, UT, United States","start_date":"2018-06-18","name":"CVF: Conference on Computer Vision and Pattern Recognition"},"doi":"10.1109/cvpr.2018.00956","publication_identifier":{"eissn":["2575-7075"],"isbn":["9781538664209"]},"quality_controlled":"1","status":"public","type":"conference","article_processing_charge":"No","arxiv":1,"date_published":"2018-12-17T00:00:00Z","year":"2018","date_created":"2022-03-18T12:45:09Z","isi":1,"language":[{"iso":"eng"}],"oa":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"}],"month":"12","external_id":{"isi":["000457843609036"],"arxiv":["1712.08087"]},"corr_author":"1","publication_status":"published","author":[{"first_name":"Jasper","last_name":"Uijlings","full_name":"Uijlings, Jasper"},{"full_name":"Konyushkova, Ksenia","first_name":"Ksenia","last_name":"Konyushkova"},{"orcid":"0000-0001-8622-7887","full_name":"Lampert, Christoph","id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","first_name":"Christoph","last_name":"Lampert"},{"full_name":"Ferrari, Vittorio","last_name":"Ferrari","first_name":"Vittorio"}]},{"arxiv":1,"article_processing_charge":"No","extern":"1","type":"conference","status":"public","quality_controlled":"1","doi":"10.1109/cvpr.2018.00202","publication_identifier":{"isbn":["9781538664216"],"eissn":["2575-7075"]},"conference":{"end_date":"2018-06-23","name":"31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition","start_date":"2018-06-18","location":"Salt Lake City, UT, United States"},"user_id":"3E5EF7F0-F248-11E8-B48F-1D18A9856A87","scopus_import":"1","oa_version":"Preprint","date_updated":"2024-12-05T14:40:39Z","day":"16","publisher":"IEEE","main_file_link":[{"url":"https://doi.org/10.48550/arXiv.1712.00268","open_access":"1"}],"citation":{"ista":"Litany O, Bronstein AM, Bronstein M, Makadia A. 2018. Deformable shape completion with graph convolutional autoencoders. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. 31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 8578300.","chicago":"Litany, Or, Alex M. Bronstein, Michael Bronstein, and Ameesh Makadia. “Deformable Shape Completion with Graph Convolutional Autoencoders.” In <i>2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition</i>. IEEE, 2018. <a href=\"https://doi.org/10.1109/cvpr.2018.00202\">https://doi.org/10.1109/cvpr.2018.00202</a>.","short":"O. Litany, A.M. Bronstein, M. Bronstein, A. Makadia, in:, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, IEEE, 2018.","apa":"Litany, O., Bronstein, A. M., Bronstein, M., &#38; Makadia, A. (2018). Deformable shape completion with graph convolutional autoencoders. In <i>2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition</i>. Salt Lake City, UT, United States: IEEE. <a href=\"https://doi.org/10.1109/cvpr.2018.00202\">https://doi.org/10.1109/cvpr.2018.00202</a>","mla":"Litany, Or, et al. “Deformable Shape Completion with Graph Convolutional Autoencoders.” <i>2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition</i>, 8578300, IEEE, 2018, doi:<a href=\"https://doi.org/10.1109/cvpr.2018.00202\">10.1109/cvpr.2018.00202</a>.","ieee":"O. Litany, A. M. Bronstein, M. Bronstein, and A. Makadia, “Deformable shape completion with graph convolutional autoencoders,” in <i>2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition</i>, Salt Lake City, UT, United States, 2018.","ama":"Litany O, Bronstein AM, Bronstein M, Makadia A. Deformable shape completion with graph convolutional autoencoders. In: <i>2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition</i>. IEEE; 2018. doi:<a href=\"https://doi.org/10.1109/cvpr.2018.00202\">10.1109/cvpr.2018.00202</a>"},"publication":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition","_id":"18270","title":"Deformable shape completion with graph convolutional autoencoders","author":[{"full_name":"Litany, Or","first_name":"Or","last_name":"Litany"},{"orcid":"0000-0001-9699-8730","full_name":"Bronstein, Alexander","id":"58f3726e-7cba-11ef-ad8b-e6e8cb3904e6","first_name":"Alexander","last_name":"Bronstein"},{"last_name":"Bronstein","first_name":"Michael","full_name":"Bronstein, Michael"},{"last_name":"Makadia","first_name":"Ameesh","full_name":"Makadia, Ameesh"}],"article_number":"8578300","publication_status":"published","external_id":{"arxiv":["1712.00268"]},"month":"12","abstract":[{"lang":"eng","text":"The availability of affordable and portable depth sensors has made scanning objects and people simpler than ever. However, dealing with occlusions and missing parts is still a significant challenge. The problem of reconstructing a (possibly non-rigidly moving) 3D object from a single or multiple partial scans has received increasing attention in recent years. In this work, we propose a novel learning-based method for the completion of partial shapes. Unlike the majority of existing approaches, our method focuses on objects that can undergo non-rigid deformations. The core of our method is a variational autoencoder with graph convolutional operations that learns a latent space for complete realistic shapes. At inference, we optimize to find the representation in this latent space that best fits the generated shape to the known partial input. The completed shape exhibits a realistic appearance on the unknown part. We show promising results towards the completion of synthetic and real scans of human body and face meshes exhibiting different styles of articulation and partiality."}],"language":[{"iso":"eng"}],"oa":1,"date_created":"2024-10-09T07:41:53Z","year":"2018","date_published":"2018-12-16T00:00:00Z"}]