{"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-spatial-semantic-relationship-for","title":"Learning Spatial-Semantic Relationship for Facial Attribute Recognition With Limited Labeled Data","arxiv_id":null,"date":"2021-06-19","proceeding":"CVPR 2021 1","authors":["Ying Shu","Yan Yan","Si Chen","Jing-Hao Xue","Chunhua Shen","Hanzi Wang"],"abstract":"    Recent advances in deep learning have demonstrated excellent results for Facial Attribute Recognition (FAR), typically trained with large-scale labeled data. However, in many real-world FAR applications, only limited labeled data are available, leading to remarkable deterioration in performance for most existing deep learning-based FAR methods. To address this problem, here we propose a method termed Spatial-Semantic Patch Learning (SSPL). The training of SSPL involves two stages. First, three auxiliary tasks, consisting of a Patch Rotation Task (PRT), a Patch Segmentation Task (PST), and a Patch Classification Task (PCT), are jointly developed to learn the spatial-semantic relationship from large-scale unlabeled facial data. We thus obtain a powerful pre-trained model. In particular, PRT exploits the spatial information of facial images in a self-supervised learning manner. PST and PCT respectively capture the pixel-level and image-level semantic information of facial images based on a facial parsing model. Second, the spatial-semantic knowledge learned from auxiliary tasks is transferred to the FAR task. By doing so, it enables that only a limited number of labeled data are required to fine-tune the pre-trained model. We achieve superior performance compared with state-of-the-art methods, as substantiated by extensive experiments and studies.    ","url_abs":"http://openaccess.thecvf.com//content/CVPR2021/html/Shu_Learning_Spatial-Semantic_Relationship_for_Facial_Attribute_Recognition_With_Limited_Labeled_CVPR_2021_paper.html","url_pdf":"http://openaccess.thecvf.com//content/CVPR2021/papers/Shu_Learning_Spatial-Semantic_Relationship_for_Facial_Attribute_Recognition_With_Limited_Labeled_CVPR_2021_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":[],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"facial-attribute-classification","task_name":"Facial Attribute Classification"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"}],"methods":[{"method_slug":"pct","method_name":"PCT"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/facial-attribute-classification-on-lfwa","task":"Facial Attribute Classification","dataset":"LFWA","model":"SSPL","rank_in_archive_order":3,"of":7,"metrics":{"Error Rate":"13.47"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}