{"publication":"Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition","month":"09","user_id":"4435EBFC-F248-11E8-B48F-1D18A9856A87","date_updated":"2024-10-09T20:55:34Z","title":"Deep Fisher Kernels – End to end learning of the Fisher Kernel GMM parameters","publisher":"IEEE","corr_author":"1","page":"1402 - 1409","doi":"10.1109/CVPR.2014.182","status":"public","department":[{"_id":"ChLa"}],"day":"24","publication_status":"published","conference":{"name":"CVPR: Computer Vision and Pattern Recognition","location":"Columbus, USA","start_date":"2014-06-23","end_date":"2014-06-28"},"scopus_import":1,"ec_funded":1,"date_created":"2018-12-11T11:56:08Z","citation":{"apa":"Sydorov, V., Sakurada, M., &#38; Lampert, C. (2014). Deep Fisher Kernels – End to end learning of the Fisher Kernel GMM parameters. In <i>Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition</i> (pp. 1402–1409). Columbus, USA: IEEE. <a href=\"https://doi.org/10.1109/CVPR.2014.182\">https://doi.org/10.1109/CVPR.2014.182</a>","chicago":"Sydorov, Vladyslav, Mayu Sakurada, and Christoph Lampert. “Deep Fisher Kernels – End to End Learning of the Fisher Kernel GMM Parameters.” In <i>Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition</i>, 1402–9. IEEE, 2014. <a href=\"https://doi.org/10.1109/CVPR.2014.182\">https://doi.org/10.1109/CVPR.2014.182</a>.","ama":"Sydorov V, Sakurada M, Lampert C. Deep Fisher Kernels – End to end learning of the Fisher Kernel GMM parameters. In: <i>Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition</i>. IEEE; 2014:1402-1409. doi:<a href=\"https://doi.org/10.1109/CVPR.2014.182\">10.1109/CVPR.2014.182</a>","ieee":"V. Sydorov, M. Sakurada, and C. Lampert, “Deep Fisher Kernels – End to end learning of the Fisher Kernel GMM parameters,” in <i>Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition</i>, Columbus, USA, 2014, pp. 1402–1409.","ista":"Sydorov V, Sakurada M, Lampert C. 2014. Deep Fisher Kernels – End to end learning of the Fisher Kernel GMM parameters. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR: Computer Vision and Pattern Recognition, 1402–1409.","short":"V. Sydorov, M. Sakurada, C. Lampert, in:, Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, IEEE, 2014, pp. 1402–1409.","mla":"Sydorov, Vladyslav, et al. “Deep Fisher Kernels – End to End Learning of the Fisher Kernel GMM Parameters.” <i>Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition</i>, IEEE, 2014, pp. 1402–09, doi:<a href=\"https://doi.org/10.1109/CVPR.2014.182\">10.1109/CVPR.2014.182</a>."},"publist_id":"4812","abstract":[{"lang":"eng","text":"Fisher Kernels and Deep Learning were two developments with significant impact on large-scale object categorization in the last years. Both approaches were shown to achieve state-of-the-art results on large-scale object categorization datasets, such as ImageNet. Conceptually, however, they are perceived as very different and it is not uncommon for heated debates to spring up when advocates of both paradigms meet at conferences or workshops. In this work, we emphasize the similarities between both architectures rather than their differences and we argue that such a unified view allows us to transfer ideas from one domain to the other. As a concrete example we introduce a method for learning a support vector machine classifier with Fisher kernel at the same time as a task-specific data representation. We reinterpret the setting as a multi-layer feed forward network. Its final layer is the classifier, parameterized by a weight vector, and the two previous layers compute Fisher vectors, parameterized by the coefficients of a Gaussian mixture model. We introduce a gradient descent based learning algorithm that, in contrast to other feature learning techniques, is not just derived from intuition or biological analogy, but has a theoretical justification in the framework of statistical learning theory. Our experiments show that the new training procedure leads to significant improvements in classification accuracy while preserving the modularity and geometric interpretability of a support vector machine setup."}],"author":[{"full_name":"Sydorov, Vladyslav","last_name":"Sydorov","first_name":"Vladyslav"},{"first_name":"Mayu","last_name":"Sakurada","full_name":"Sakurada, Mayu"},{"first_name":"Christoph","last_name":"Lampert","full_name":"Lampert, Christoph","id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","orcid":"0000-0001-8622-7887"}],"type":"conference","language":[{"iso":"eng"}],"_id":"2172","year":"2014","quality_controlled":"1","date_published":"2014-09-24T00:00:00Z","oa_version":"None","project":[{"grant_number":"308036","_id":"2532554C-B435-11E9-9278-68D0E5697425","call_identifier":"FP7","name":"Lifelong Learning of Visual Scene Understanding"}]}