{"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/a-distilled-model-for-tracking-and-tracker","title":"Tracking-by-Trackers with a Distilled and Reinforced Model","arxiv_id":"2007.04108","date":"2020-07-08","proceeding":null,"authors":["Matteo Dunnhofer","Niki Martinel","Christian Micheloni"],"abstract":"Visual object tracking was generally tackled by reasoning independently on fast processing algorithms, accurate online adaptation methods, and fusion of trackers. In this paper, we unify such goals by proposing a novel tracking methodology that takes advantage of other visual trackers, offline and online. A compact student model is trained via the marriage of knowledge distillation and reinforcement learning. The first allows to transfer and compress tracking knowledge of other trackers. The second enables the learning of evaluation measures which are then exploited online. After learning, the student can be ultimately used to build (i) a very fast single-shot tracker, (ii) a tracker with a simple and effective online adaptation mechanism, (iii) a tracker that performs fusion of other trackers. Extensive validation shows that the proposed algorithms compete with real-time state-of-the-art trackers.","url_abs":"https://arxiv.org/abs/2007.04108v2","url_pdf":"https://arxiv.org/pdf/2007.04108v2.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":"a-distilled-model-for-tracking-and-tracker","repo_url":"https://github.com/dontfollowmeimcrazy/vot-kd-rl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"},{"task_slug":"object-tracking","task_name":"Object Tracking"},{"task_slug":"video-object-tracking","task_name":"Video Object Tracking"},{"task_slug":"visual-object-tracking","task_name":"Visual Object Tracking"},{"task_slug":"visual-tracking","task_name":"Visual Tracking"}],"methods":[{"method_slug":"knowledge-distillation","method_name":"Knowledge Distillation"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-object-tracking-on-nv-vot211","task":"Video Object Tracking","dataset":"NT-VOT211","model":"TRAS","rank_in_archive_order":39,"of":43,"metrics":{"AUC":"23.58","Precision":"30.64"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-got-10k","task":"Visual Object Tracking","dataset":"GOT-10k","model":"TRASFUST","rank_in_archive_order":38,"of":42,"metrics":{"Average Overlap":"61.7","Success Rate 0.5":"72.9"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-lasot","task":"Visual Object Tracking","dataset":"LaSOT","model":"TRASFUST","rank_in_archive_order":41,"of":46,"metrics":{"AUC":"57.6"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-otb-2015","task":"Visual Object Tracking","dataset":"OTB-2015","model":"TRASFUST","rank_in_archive_order":9,"of":18,"metrics":{"AUC":"0.701","Precision":"0.931"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-uav123","task":"Visual Object Tracking","dataset":"UAV123","model":"TRASFUST","rank_in_archive_order":13,"of":16,"metrics":{"AUC":"0.679","Precision":"0.873"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}