{"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/improving-task-adaptation-for-cross-domain","title":"Cross-domain Few-shot Learning with Task-specific Adapters","arxiv_id":"2107.00358","date":"2021-07-01","proceeding":"CVPR 2022 1","authors":["Wei-Hong Li","Xialei Liu","Hakan Bilen"],"abstract":"In this paper, we look at the problem of cross-domain few-shot classification that aims to learn a classifier from previously unseen classes and domains with few labeled samples. Recent approaches broadly solve this problem by parameterizing their few-shot classifiers with task-agnostic and task-specific weights where the former is typically learned on a large training set and the latter is dynamically predicted through an auxiliary network conditioned on a small support set. In this work, we focus on the estimation of the latter, and propose to learn task-specific weights from scratch directly on a small support set, in contrast to dynamically estimating them. In particular, through systematic analysis, we show that task-specific weights through parametric adapters in matrix form with residual connections to multiple intermediate layers of a backbone network significantly improves the performance of the state-of-the-art models in the Meta-Dataset benchmark with minor additional cost.","url_abs":"https://arxiv.org/abs/2107.00358v4","url_pdf":"https://arxiv.org/pdf/2107.00358v4.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":"improving-task-adaptation-for-cross-domain","repo_url":"https://github.com/VICO-UoE/URL","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"improving-task-adaptation-for-cross-domain","repo_url":"https://github.com/google-research/meta-dataset","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"improving-task-adaptation-for-cross-domain","repo_url":"https://github.com/jimzai/deta","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"improving-task-adaptation-for-cross-domain","repo_url":"https://github.com/nobody-1617/deta","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"cross-domain-few-shot","task_name":"Cross-Domain Few-Shot"},{"task_slug":"few-shot-image-classification","task_name":"Few-Shot Image Classification"},{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"},{"task_slug":"cross-domain-few-shot-learning","task_name":"cross-domain few-shot learning"}],"methods":[{"method_slug":"adapter","method_name":"Adapter"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/few-shot-image-classification-on-meta-dataset","task":"Few-Shot Image Classification","dataset":"Meta-Dataset","model":"TSA (ResNet18, URL, residual adapters, 84x84 image, shuffled data, scratch, MDL)","rank_in_archive_order":4,"of":22,"metrics":{"Accuracy":"78.07"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2107.00358","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}