{"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/deep-multi-center-learning-for-face-alignment","title":"Deep Multi-Center Learning for Face Alignment","arxiv_id":"1808.01558","date":"2018-08-05","proceeding":null,"authors":["Zhiwen Shao","Hengliang Zhu","Xin Tan","Yangyang Hao","Lizhuang Ma"],"abstract":"Facial landmarks are highly correlated with each other since a certain\nlandmark can be estimated by its neighboring landmarks. Most of the existing\ndeep learning methods only use one fully-connected layer called shape\nprediction layer to estimate the locations of facial landmarks. In this paper,\nwe propose a novel deep learning framework named Multi-Center Learning with\nmultiple shape prediction layers for face alignment. In particular, each shape\nprediction layer emphasizes on the detection of a certain cluster of\nsemantically relevant landmarks respectively. Challenging landmarks are focused\nfirstly, and each cluster of landmarks is further optimized respectively.\nMoreover, to reduce the model complexity, we propose a model assembling method\nto integrate multiple shape prediction layers into one shape prediction layer.\nExtensive experiments demonstrate that our method is effective for handling\ncomplex occlusions and appearance variations with real-time performance. The\ncode for our method is available at\nhttps://github.com/ZhiwenShao/MCNet-Extension.","url_abs":"http://arxiv.org/abs/1808.01558v2","url_pdf":"http://arxiv.org/pdf/1808.01558v2.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":"deep-multi-center-learning-for-face-alignment","repo_url":"https://github.com/ZhiwenShao/MCNet-Extension","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"face-alignment","task_name":"Face Alignment"},{"task_slug":"prediction","task_name":"Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/face-alignment-on-aflw2000","task":"Face Alignment","dataset":"AFLW2000","model":"MCL","rank_in_archive_order":3,"of":5,"metrics":{"Error rate":"5.38"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}