{"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/semi-supervised-learning-with-self-supervised","title":"Exploring Self-Supervised Regularization for Supervised and Semi-Supervised Learning","arxiv_id":"1906.10343","date":"2019-06-25","proceeding":null,"authors":["Phi Vu Tran"],"abstract":"Recent advances in semi-supervised learning have shown tremendous potential in overcoming a major barrier to the success of modern machine learning algorithms: access to vast amounts of human-labeled training data. Previous algorithms based on consistency regularization can harness the abundance of unlabeled data to produce impressive results on a number of semi-supervised benchmarks, approaching the performance of strong supervised baselines using only a fraction of the available labeled data. In this work, we challenge the long-standing success of consistency regularization by introducing self-supervised regularization as the basis for combining semantic feature representations from unlabeled data. We perform extensive comparative experiments to demonstrate the effectiveness of self-supervised regularization for supervised and semi-supervised image classification on SVHN, CIFAR-10, and CIFAR-100 benchmark datasets. We present two main results: (1) models augmented with self-supervised regularization significantly improve upon traditional supervised classifiers without the need for unlabeled data; (2) together with unlabeled data, our models yield semi-supervised performance competitive with, and in many cases exceeding, prior state-of-the-art consistency baselines. Lastly, our models have the practical utility of being efficiently trained end-to-end and require no additional hyper-parameters to tune for optimal performance beyond the standard set for training neural networks. Reference code and data are available at https://github.com/vuptran/sesemi","url_abs":"https://arxiv.org/abs/1906.10343v2","url_pdf":"https://arxiv.org/pdf/1906.10343v2.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":"semi-supervised-learning-with-self-supervised","repo_url":"https://github.com/vuptran/sesemi","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"},{"task_slug":"semi-supervised-image-classification","task_name":"Semi-Supervised Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/semi-supervised-image-classification-on-cifar-11","task":"Semi-Supervised Image Classification","dataset":"CIFAR-10, 1000 Labels","model":"SESEMI SSL (ConvNet)","rank_in_archive_order":8,"of":9,"metrics":{"Accuracy":"82.12"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-cifar-12","task":"Semi-Supervised Image Classification","dataset":"CIFAR-10, 2000 Labels","model":"SESEMI SSL (ConvNet)","rank_in_archive_order":4,"of":4,"metrics":{"Accuracy":"85.78"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-cifar","task":"Semi-Supervised Image Classification","dataset":"CIFAR-10, 4000 Labels","model":"SESEMI SSL (ConvNet)","rank_in_archive_order":44,"of":49,"metrics":{"Percentage error":"11.65"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-svhn","task":"Semi-Supervised Image Classification","dataset":"SVHN, 1000 labels","model":"SESEMI SSL (ConvNet)","rank_in_archive_order":16,"of":17,"metrics":{"Accuracy":"94.41"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-svhn-1","task":"Semi-Supervised Image Classification","dataset":"SVHN, 250 Labels","model":"SESEMI SSL (ConvNet)","rank_in_archive_order":12,"of":15,"metrics":{"Accuracy":"91.68"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-svhn-3","task":"Semi-Supervised Image Classification","dataset":"SVHN, 500 Labels","model":"SESEMI SSL (ConvNet)","rank_in_archive_order":6,"of":6,"metrics":{"Accuracy":"93.5"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-cifar-2","task":"Semi-Supervised Image Classification","dataset":"cifar-100, 10000 Labels","model":"SESEMI SSL (ConvNet)","rank_in_archive_order":28,"of":29,"metrics":{"Percentage error":"38.7"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}