{"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/invariant-feature-regularization-for-fair-1","title":"Invariant Feature Regularization for Fair Face Recognition","arxiv_id":"2310.14652","date":"2023-10-23","proceeding":"ICCV 2023 1","authors":["Jiali Ma","Zhongqi Yue","Kagaya Tomoyuki","Suzuki Tomoki","Karlekar Jayashree","Sugiri Pranata","Hanwang Zhang"],"abstract":"Fair face recognition is all about learning invariant feature that generalizes to unseen faces in any demographic group. Unfortunately, face datasets inevitably capture the imbalanced demographic attributes that are ubiquitous in real-world observations, and the model learns biased feature that generalizes poorly in the minority group. We point out that the bias arises due to the confounding demographic attributes, which mislead the model to capture the spurious demographic-specific feature. The confounding effect can only be removed by causal intervention, which requires the confounder annotations. However, such annotations can be prohibitively expensive due to the diversity of the demographic attributes. To tackle this, we propose to generate diverse data partitions iteratively in an unsupervised fashion. Each data partition acts as a self-annotated confounder, enabling our Invariant Feature Regularization (INV-REG) to deconfound. INV-REG is orthogonal to existing methods, and combining INV-REG with two strong baselines (Arcface and CIFP) leads to new state-of-the-art that improves face recognition on a variety of demographic groups. Code is available at https://github.com/PanasonicConnect/InvReg.","url_abs":"https://arxiv.org/abs/2310.14652v1","url_pdf":"https://arxiv.org/pdf/2310.14652v1.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":"invariant-feature-regularization-for-fair-1","repo_url":"https://github.com/milliema/invreg","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"invariant-feature-regularization-for-fair-1","repo_url":"https://github.com/panasonicconnect/invreg","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"invariant-feature-regularization-for-fair-1","repo_url":"https://github.com/Recognito-Vision/Face-SDK-Linux-Demos","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"face-recognition","task_name":"Face Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2310.14652","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.14652"}},"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/panasonicconnect/invreg","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Recognito-Vision/Face-SDK-Linux-Demos","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/milliema/invreg","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/milliema/InvReg","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":2,"ran_fixture":1,"unverified":1},"by_repo_kind":{"official":{"samples":4,"ran":3,"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":0,"samples":[{"code_sha256_prefix":"1736503522b025e1","entry":"AllGather","repo":"panasonicconnect/invreg","repo_kind":"official","path":"utils/utils_invreg.py","file_url":"https://github.com/panasonicconnect/invreg/blob/HEAD/utils/utils_invreg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1736503522b025e1"}},{"code_sha256_prefix":"3ab310efaf89176b","entry":"DistAllGather","repo":"panasonicconnect/invreg","repo_kind":"official","path":"utils/utils_invreg.py","file_url":"https://github.com/panasonicconnect/invreg/blob/HEAD/utils/utils_invreg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3ab310efaf89176b"}},{"code_sha256_prefix":"6a8ca1053b179d97","entry":"all_reduce","repo":"panasonicconnect/invreg","repo_kind":"official","path":"utils/utils_invreg.py","file_url":"https://github.com/panasonicconnect/invreg/blob/HEAD/utils/utils_invreg.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6a8ca1053b179d97"}},{"code_sha256_prefix":"7bb0c00f22d2ba09","entry":"env_loss_ce_ddp","repo":"panasonicconnect/invreg","repo_kind":"official","path":"utils/utils_invreg.py","file_url":"https://github.com/panasonicconnect/invreg/blob/HEAD/utils/utils_invreg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7bb0c00f22d2ba09"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}