{"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/task-decoupled-knowledge-distillation-for","title":"Task Decoupled Knowledge Distillation For Lightweight Face Detectors","arxiv_id":null,"date":"2020-10-14","proceeding":null,"authors":["Xiaoqing Liang","Xu Zhao","Chaoyang Zhao","Nanfei Jiang","Ming Tang","Jinqiao Wang"],"abstract":"We propose a knowledge distillation method for the face detection task. This method decouples the distillation task of face detection into two subtasks, i.e., the classification distillation subtask and the regression distillation subtask. We add the task-specific convolutions in the teacher network and add the adaption convolutions on the feature maps of the student network to generate the task decoupled features. Then, each subtask uses different samples in distilling the features to be consistent with the corresponding detection subtask. Moreover, we propose an effective probability distillation method to joint boost the accuracy of the student network.","url_abs":"https://www.researchgate.net/publication/346172975_Task_Decoupled_Knowledge_Distillation_For_Lightweight_Face_Detectors","url_pdf":"https://www.researchgate.net/profile/Xu-Zhao-19/publication/346172975_Task_Decoupled_Knowledge_Distillation_For_Lightweight_Face_Detectors/links/5fc75592a6fdcc697bd355e1/Task-Decoupled-Knowledge-Distillation-For-Lightweight-Face-Detectors.pdf?_sg%5B0%5D=ZSZXAWiYHmRnxLG9tqveby6G5vrU1XCimaltgLdRJc1nGb-FiqTIe2IShHOBP-gE6NnYC_05eJqIs3rkJsx9Rg.JOcEVXYnQdlpTCFGTGxwd9gihuPtwLIpQIa4WNbb6PpXJ5-nScC5S4wF3OFADt1t09tiyP4qQFiFOs-EhJPC5Q&_sg%5B1%5D=LOYWouAhtY7FX8frCBKIPT39cjlfE2fKXDD-Mu4z2WkLz2zkfnZ2XdrkhT_oBUl4bL1WlGx87j8sJ-YwPd-mEW3O-BntvJvBLSqgzMPYgq5K.JOcEVXYnQdlpTCFGTGxwd9gihuPtwLIpQIa4WNbb6PpXJ5-nScC5S4wF3OFADt1t09tiyP4qQFiFOs-EhJPC5Q&_sg%5B2%5D=tCL-HDHjA3TY0epJ-O8HVwmM9uI9soGj5eOHMR6CnRo4p3aVgzWDD2wDFHTTYd971egfn8ChePLH9hU.FqOFeozsnhNq_xnobD0hV8YlhSvQDXyOAzR21ySWshpkvjC8UK0hJwyjCOHI97IQZ6nqx5r6lg3q0qQXEDQ2cA&_iepl=","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":"task-decoupled-knowledge-distillation-for","repo_url":"https://github.com/CASIA-IVA-Lab/TDKD","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"face-detection","task_name":"Face Detection"},{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"},{"task_slug":"regression-1","task_name":"regression"}],"methods":[{"method_slug":"knowledge-distillation","method_name":"Knowledge Distillation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}