{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/self-supervised-classification-network","title":"Self-Supervised Classification Network","arxiv_id":"2103.10994","date":"2021-03-19","proceeding":null,"authors":["Elad Amrani","Leonid Karlinsky","Alex Bronstein"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2103.10994v3","url_pdf":"https://arxiv.org/pdf/2103.10994v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"self-supervised-classification-network","repo_url":"https://github.com/elad-amrani/self-classifier","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"self-supervised-classification-network","repo_url":"https://github.com/abhsri/Reimplementation-of-Self-supervised-Classifier","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"self-supervised-image-classification","task_name":"Self-Supervised Image Classification"},{"task_slug":"unsupervised-image-classification","task_name":"Unsupervised Image Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/self-supervised-image-classification-on","task":"Self-Supervised Image Classification","dataset":"ImageNet","model":"Self-Classifier (ResNet-50)","rank_in_archive_order":87,"of":144,"metrics":{"Number of Params":"24M","Top 1 Accuracy":"74.2%"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-image-classification-on-imagenet","task":"Unsupervised Image Classification","dataset":"ImageNet","model":"Self-Classifier (ResNet-50)","rank_in_archive_order":5,"of":9,"metrics":{"ARI":"29.5","Accuracy (%)":"41.1"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2103.10994","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}