{"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/heterogeneous-face-attribute-estimation-a","title":"Heterogeneous Face Attribute Estimation: A Deep Multi-Task Learning Approach","arxiv_id":"1706.00906","date":"2017-06-03","proceeding":null,"authors":["Hu Han","Anil K. Jain","Fang Wang","Shiguang Shan","Xilin Chen"],"abstract":"Face attribute estimation has many potential applications in video\nsurveillance, face retrieval, and social media. While a number of methods have\nbeen proposed for face attribute estimation, most of them did not explicitly\nconsider the attribute correlation and heterogeneity (e.g., ordinal vs. nominal\nand holistic vs. local) during feature representation learning. In this paper,\nwe present a Deep Multi-Task Learning (DMTL) approach to jointly estimate\nmultiple heterogeneous attributes from a single face image. In DMTL, we tackle\nattribute correlation and heterogeneity with convolutional neural networks\n(CNNs) consisting of shared feature learning for all the attributes, and\ncategory-specific feature learning for heterogeneous attributes. We also\nintroduce an unconstrained face database (LFW+), an extension of public-domain\nLFW, with heterogeneous demographic attributes (age, gender, and race) obtained\nvia crowdsourcing. Experimental results on benchmarks with multiple face\nattributes (MORPH II, LFW+, CelebA, LFWA, and FotW) show that the proposed\napproach has superior performance compared to state of the art. Finally,\nevaluations on a public-domain face database (LAP) with a single attribute show\nthat the proposed approach has excellent generalization ability.","url_abs":"http://arxiv.org/abs/1706.00906v3","url_pdf":"http://arxiv.org/pdf/1706.00906v3.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":"attribute","task_name":"Attribute"},{"task_slug":"facial-attribute-classification","task_name":"Facial Attribute Classification"},{"task_slug":"morph","task_name":"MORPH"},{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/facial-attribute-classification-on-lfwa","task":"Facial Attribute Classification","dataset":"LFWA","model":"DMTL","rank_in_archive_order":5,"of":7,"metrics":{"Error Rate":"13.85"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1706.00906","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}