{"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/test-time-training-for-out-of-distribution-1","title":"Test-Time Training with Self-Supervision for Generalization under Distribution Shifts","arxiv_id":"1909.13231","date":"2019-09-29","proceeding":null,"authors":["Yu Sun","Xiaolong Wang","Zhuang Liu","John Miller","Alexei A. Efros","Moritz Hardt"],"abstract":"In this paper, we propose Test-Time Training, a general approach for improving the performance of predictive models when training and test data come from different distributions. We turn a single unlabeled test sample into a self-supervised learning problem, on which we update the model parameters before making a prediction. This also extends naturally to data in an online stream. Our simple approach leads to improvements on diverse image classification benchmarks aimed at evaluating robustness to distribution shifts.","url_abs":"https://arxiv.org/abs/1909.13231v3","url_pdf":"https://arxiv.org/pdf/1909.13231v3.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":"test-time-training-for-out-of-distribution-1","repo_url":"https://github.com/yueatsprograms/ttt_cifar_release","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"test-time-training-for-out-of-distribution-1","repo_url":"https://github.com/yueatsprograms/ttt_imagenet_release","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"test-time-training-for-out-of-distribution-1","repo_url":"https://github.com/tejas-gokhale/AGAT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"building-change-detection-for-remote-sensing","task_name":"Building change detection for remote sensing images"},{"task_slug":"carla-map-leaderboard","task_name":"CARLA MAP Leaderboard"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"low-light-image-enhancement","task_name":"Low-Light Image Enhancement"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"},{"task_slug":"supervised-video-summarization","task_name":"Supervised Video Summarization"},{"task_slug":"video-quality-assessment","task_name":"Video Quality Assessment"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/language-modelling-on-lambada","task":"Language Modelling","dataset":"LAMBADA","model":"test","rank_in_archive_order":34,"of":37,"metrics":{"Accuracy":"0.01"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1909.13231","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}