{"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/orthogonal-deep-features-decomposition-for","title":"Orthogonal Deep Features Decomposition for Age-Invariant Face Recognition","arxiv_id":"1810.07599","date":"2018-10-17","proceeding":"ECCV 2018 9","authors":["Yitong Wang","Dihong Gong","Zheng Zhou","Xing Ji","Hao Wang","Zhifeng Li","Wei Liu","Tong Zhang"],"abstract":"As facial appearance is subject to significant intra-class variations caused\nby the aging process over time, age-invariant face recognition (AIFR) remains a\nmajor challenge in face recognition community. To reduce the intra-class\ndiscrepancy caused by the aging, in this paper we propose a novel approach\n(namely, Orthogonal Embedding CNNs, or OE-CNNs) to learn the age-invariant deep\nface features. Specifically, we decompose deep face features into two\northogonal components to represent age-related and identity-related features.\nAs a result, identity-related features that are robust to aging are then used\nfor AIFR. Besides, for complementing the existing cross-age datasets and\nadvancing the research in this field, we construct a brand-new large-scale\nCross-Age Face dataset (CAF). Extensive experiments conducted on the three\npublic domain face aging datasets (MORPH Album 2, CACD-VS and FG-NET) have\nshown the effectiveness of the proposed approach and the value of the\nconstructed CAF dataset on AIFR. Benchmarking our algorithm on one of the most\npopular general face recognition (GFR) dataset LFW additionally demonstrates\nthe comparable generalization performance on GFR.","url_abs":"http://arxiv.org/abs/1810.07599v1","url_pdf":"http://arxiv.org/pdf/1810.07599v1.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":[],"tasks":[{"task_slug":"age-invariant-face-recognition","task_name":"Age-Invariant Face Recognition"},{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":"face-recognition","task_name":"Face Recognition"},{"task_slug":"morph","task_name":"MORPH"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/age-invariant-face-recognition-on-cacdvs","task":"Age-Invariant Face Recognition","dataset":"CACDVS","model":"OE-CNN","rank_in_archive_order":5,"of":9,"metrics":{"Accuracy":"99.2%"},"uses_additional_data":false},{"leaderboard":"/sota/age-invariant-face-recognition-on-morph","task":"Age-Invariant Face Recognition","dataset":"MORPH Album2","model":"OE-CNN","rank_in_archive_order":3,"of":3,"metrics":{"Rank-1 Recognition Rate":"98.55%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1810.07599","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}