{"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/pcl-proxy-based-contrastive-learning-for","title":"PCL: Proxy-Based Contrastive Learning for Domain Generalization","arxiv_id":null,"date":"2022-01-01","proceeding":"CVPR 2022 1","authors":["Xufeng Yao","Yang Bai","Xinyun Zhang","Yuechen Zhang","Qi Sun","Ran Chen","Ruiyu Li","Bei Yu"],"abstract":"    Domain generalization refers to the problem of training a model from a collection of different source domains that can directly generalize to the unseen target domains. A promising solution is contrastive learning, which attempts to learn domain-invariant representations by exploiting rich semantic relations among sample-to-sample pairs from different domains. A simple approach is to pull positive sample pairs from different domains closer while pushing other negative pairs further apart. In this paper, we find that directly applying contrastive-based methods (e.g., supervised contrastive learning) are not effective in domain generalization. We argue that aligning positive sample-to-sample pairs tends to hinder the model generalization due to the significant distribution gaps between different domains. To address this issue, we propose a novel proxy-based contrastive learning method, which replaces the original sample-to-sample relations with proxy-to-sample relations, significantly alleviating the positive alignment issue. Experiments on the four standard benchmarks demonstrate the effectiveness of the proposed method. Furthermore, we also consider a more complex scenario where no ImageNet pre-trained models are provided. Our method consistently shows better performance.    ","url_abs":"http://openaccess.thecvf.com//content/CVPR2022/html/Yao_PCL_Proxy-Based_Contrastive_Learning_for_Domain_Generalization_CVPR_2022_paper.html","url_pdf":"http://openaccess.thecvf.com//content/CVPR2022/papers/Yao_PCL_Proxy-Based_Contrastive_Learning_for_Domain_Generalization_CVPR_2022_paper.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":"pcl-proxy-based-contrastive-learning-for","repo_url":"https://github.com/yaoxufeng/PCL-Proxy-based-Contrastive-Learning-for-Domain-Generalization","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"domain-generalization","task_name":"Domain Generalization"}],"methods":[{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/domain-generalization-on-office-home","task":"Domain Generalization","dataset":"Office-Home","model":"PCL (swad+resnet50)","rank_in_archive_order":27,"of":45,"metrics":{"Average Accuracy":"71.6"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-pacs-2","task":"Domain Generalization","dataset":"PACS","model":"PCL (ResNet50, SWAD)","rank_in_archive_order":23,"of":133,"metrics":{"Average Accuracy":"88.7"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}