{"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/learning-debiased-representations-via","title":"Learning Debiased Representations via Conditional Attribute Interpolation","arxiv_id":null,"date":"2023-01-01","proceeding":"CVPR 2023 1","authors":["Yi-Kai Zhang","Qi-Wei Wang","De-Chuan Zhan","Han-Jia Ye"],"abstract":"    An image is usually described by more than one attribute like \"shape\" and \"color\". When a dataset is biased, i.e., most samples have attributes spuriously correlated with the target label, a Deep Neural Network (DNN) is prone to make predictions by the \"unintended\" attribute, especially if it is easier to learn. To improve the generalization ability when training on such a biased dataset, we propose a chi^2-model to learn debiased representations. First, we design a chi-shape pattern to match the training dynamics of a DNN and find Intermediate Attribute Samples (IASs) --- samples near the attribute decision boundaries, which indicate how the value of an attribute changes from one extreme to another. Then we rectify the representation with a chi-structured metric learning objective. Conditional interpolation among IASs eliminates the negative effect of peripheral attributes and facilitates retaining the intra-class compactness. Experiments show that chi^2-model learns debiased representation effectively and achieves remarkable improvements on various datasets.    ","url_abs":"http://openaccess.thecvf.com//content/CVPR2023/html/Zhang_Learning_Debiased_Representations_via_Conditional_Attribute_Interpolation_CVPR_2023_paper.html","url_pdf":"http://openaccess.thecvf.com//content/CVPR2023/papers/Zhang_Learning_Debiased_Representations_via_Conditional_Attribute_Interpolation_CVPR_2023_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":"learning-debiased-representations-via","repo_url":"https://github.com/zhangyikaii/chi-square","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"metric-learning","task_name":"Metric Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}