{"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/fair-contrastive-learning-for-facial","title":"Fair Contrastive Learning for Facial Attribute Classification","arxiv_id":"2203.16209","date":"2022-03-30","proceeding":"CVPR 2022 1","authors":["Sungho Park","Jewook Lee","Pilhyeon Lee","Sunhee Hwang","Dohyung Kim","Hyeran Byun"],"abstract":"Learning visual representation of high quality is essential for image classification. Recently, a series of contrastive representation learning methods have achieved preeminent success. Particularly, SupCon outperformed the dominant methods based on cross-entropy loss in representation learning. However, we notice that there could be potential ethical risks in supervised contrastive learning. In this paper, we for the first time analyze unfairness caused by supervised contrastive learning and propose a new Fair Supervised Contrastive Loss (FSCL) for fair visual representation learning. Inheriting the philosophy of supervised contrastive learning, it encourages representation of the same class to be closer to each other than that of different classes, while ensuring fairness by penalizing the inclusion of sensitive attribute information in representation. In addition, we introduce a group-wise normalization to diminish the disparities of intra-group compactness and inter-class separability between demographic groups that arouse unfair classification. Through extensive experiments on CelebA and UTK Face, we validate that the proposed method significantly outperforms SupCon and existing state-of-the-art methods in terms of the trade-off between top-1 accuracy and fairness. Moreover, our method is robust to the intensity of data bias and effectively works in incomplete supervised settings. Our code is available at https://github.com/sungho-CoolG/FSCL.","url_abs":"https://arxiv.org/abs/2203.16209v1","url_pdf":"https://arxiv.org/pdf/2203.16209v1.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":"fair-contrastive-learning-for-facial","repo_url":"https://github.com/sungho-coolg/fscl","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":"classification-1","task_name":"Classification"},{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"facial-attribute-classification","task_name":"Facial Attribute Classification"},{"task_slug":"fairness","task_name":"Fairness"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"philosophy","task_name":"Philosophy"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"},{"method_slug":"supervised-contrastive-loss","method_name":"Supervised Contrastive Loss"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2203.16209","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.16209"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sungho-coolg/fscl","reach":{"status":"ok"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/sungho-CoolG/FSCL","reach":{"status":"ok"}}],"summary":{"unverified":1},"by_repo_kind":{"official":{"samples":1,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":1,"samples":[{"code_sha256_prefix":"e516eec834afe9e4","entry":"FairSupConLoss","repo":"sungho-CoolG/FSCL","repo_kind":"official","path":"losses.py","file_url":"https://github.com/sungho-CoolG/FSCL/blob/HEAD/losses.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e516eec834afe9e4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}