{"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/ttt-ucdr-test-time-training-for-universal","title":"Test-time Training for Data-efficient UCDR","arxiv_id":"2208.09198","date":"2022-08-19","proceeding":null,"authors":["Soumava Paul","Titir Dutta","Aheli Saha","Abhishek Samanta","Soma Biswas"],"abstract":"Image retrieval under generalized test scenarios has gained significant momentum in literature, and the recently proposed protocol of Universal Cross-domain Retrieval is a pioneer in this direction. A common practice in any such generalized classification or retrieval algorithm is to exploit samples from many domains during training to learn a domain-invariant representation of data. Such criterion is often restrictive, and thus in this work, for the first time, we explore the generalized retrieval problem in a data-efficient manner. Specifically, we aim to generalize any pre-trained cross-domain retrieval network towards any unknown query domain/category, by means of adapting the model on the test data leveraging self-supervised learning techniques. Toward that goal, we explored different self-supervised loss functions~(for example, RotNet, JigSaw, Barlow Twins, etc.) and analyze their effectiveness for the same. Extensive experiments demonstrate the proposed approach is simple, easy to implement, and effective in handling data-efficient UCDR.","url_abs":"https://arxiv.org/abs/2208.09198v3","url_pdf":"https://arxiv.org/pdf/2208.09198v3.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":"ttt-ucdr-test-time-training-for-universal","repo_url":"https://github.com/mvp18/ttt-ucdr","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"sketch-based-image-retrieval","task_name":"Sketch-Based Image Retrieval"}],"methods":[{"method_slug":"barlow-twins","method_name":"Barlow Twins"},{"method_slug":"jigsaw","method_name":"Jigsaw"},{"method_slug":"rotnet","method_name":"RotNet"},{"method_slug":"test","method_name":"Test"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}