{"publication_identifier":{"eissn":["1611-3349"],"isbn":["9783031198205"],"eisbn":["9783031198212"],"issn":["0302-9743"]},"quality_controlled":"1","page":"116-132","oa":1,"volume":13691,"conference":{"name":"ECCV: European Conference on Computer Vision","location":"Tel Aviv, Israel","end_date":"2022-10-27","start_date":"2022-10-23"},"type":"conference","extern":"1","date_created":"2024-10-08T12:55:44Z","intvolume":" 13691","alternative_title":["LNCS"],"user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","oa_version":"None","doi":"10.1007/978-3-031-19821-2_7","main_file_link":[{"url":"https://doi.org/10.48550/arXiv.2103.10994","open_access":"1"}],"day":"23","publisher":"Springer Nature","publication":"17th European Conference on Computer Vision","year":"2022","related_material":{"link":[{"url":"https://github.com/elad-amrani/self-classifier","relation":"software"}]},"scopus_import":"1","external_id":{"arxiv":["2103.10994"]},"abstract":[{"lang":"eng","text":"We present Self-Classifier – a novel self-supervised end-to-end classification learning approach. Self-Classifier learns labels and representations simultaneously in a single-stage end-to-end manner by optimizing for same-class prediction of two augmented views of the same sample. To guarantee non-degenerate solutions (i.e., solutions where all labels are assigned to the same class) we propose a mathematically motivated variant of the cross-entropy loss that has a uniform prior asserted on the predicted labels. In our theoretical analysis, we prove that degenerate solutions are not in the set of optimal solutions of our approach. Self-Classifier is simple to implement and scalable. Unlike other popular unsupervised classification and contrastive representation learning approaches, it does not require any form of pre-training, expectation-maximization, pseudo-labeling, external clustering, a second network, stop-gradient operation, or negative pairs. Despite its simplicity, our approach sets a new state of the art for unsupervised classification of ImageNet; and even achieves comparable to state-of-the-art results for unsupervised representation learning. Code is available at https://github.com/elad-amrani/self-classifier."}],"_id":"18229","date_updated":"2024-10-15T07:04:39Z","article_processing_charge":"No","title":"Self-supervised classification network","date_published":"2022-10-23T00:00:00Z","publication_status":"published","citation":{"apa":"Amrani, E., Karlinsky, L., & Bronstein, A. M. (2022). Self-supervised classification network. In 17th European Conference on Computer Vision (Vol. 13691, pp. 116–132). Tel Aviv, Israel: Springer Nature. https://doi.org/10.1007/978-3-031-19821-2_7","mla":"Amrani, Elad, et al. “Self-Supervised Classification Network.” 17th European Conference on Computer Vision, vol. 13691, Springer Nature, 2022, pp. 116–32, doi:10.1007/978-3-031-19821-2_7.","ista":"Amrani E, Karlinsky L, Bronstein AM. 2022. Self-supervised classification network. 17th European Conference on Computer Vision. ECCV: European Conference on Computer Vision, LNCS, vol. 13691, 116–132.","ieee":"E. Amrani, L. Karlinsky, and A. M. Bronstein, “Self-supervised classification network,” in 17th European Conference on Computer Vision, Tel Aviv, Israel, 2022, vol. 13691, pp. 116–132.","short":"E. Amrani, L. Karlinsky, A.M. Bronstein, in:, 17th European Conference on Computer Vision, Springer Nature, 2022, pp. 116–132.","chicago":"Amrani, Elad, Leonid Karlinsky, and Alex M. Bronstein. “Self-Supervised Classification Network.” In 17th European Conference on Computer Vision, 13691:116–32. Springer Nature, 2022. https://doi.org/10.1007/978-3-031-19821-2_7.","ama":"Amrani E, Karlinsky L, Bronstein AM. Self-supervised classification network. In: 17th European Conference on Computer Vision. Vol 13691. Springer Nature; 2022:116-132. doi:10.1007/978-3-031-19821-2_7"},"status":"public","month":"10","language":[{"iso":"eng"}],"author":[{"full_name":"Amrani, Elad","last_name":"Amrani","first_name":"Elad"},{"last_name":"Karlinsky","first_name":"Leonid","full_name":"Karlinsky, Leonid"},{"orcid":"0000-0001-9699-8730","last_name":"Bronstein","first_name":"Alexander","id":"58f3726e-7cba-11ef-ad8b-e6e8cb3904e6","full_name":"Bronstein, Alexander"}]}