{"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/large-scale-object-discovery-and-detector","title":"Large-Scale Object Discovery and Detector Adaptation from Unlabeled Video","arxiv_id":"1712.08832","date":"2017-12-23","proceeding":null,"authors":["Aljoša Ošep","Paul Voigtlaender","Jonathon Luiten","Stefan Breuers","Bastian Leibe"],"abstract":"We explore object discovery and detector adaptation based on unlabeled video\nsequences captured from a mobile platform. We propose a fully automatic\napproach for object mining from video which builds upon a generic object\ntracking approach. By applying this method to three large video datasets from\nautonomous driving and mobile robotics scenarios, we demonstrate its robustness\nand generality. Based on the object mining results, we propose a novel approach\nfor unsupervised object discovery by appearance-based clustering. We show that\nthis approach successfully discovers interesting objects relevant to driving\nscenarios. In addition, we perform self-supervised detector adaptation in order\nto improve detection performance on the KITTI dataset for existing categories.\nOur approach has direct relevance for enabling large-scale object learning for\nautonomous driving.","url_abs":"http://arxiv.org/abs/1712.08832v1","url_pdf":"http://arxiv.org/pdf/1712.08832v1.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":"large-scale-object-discovery-and-detector","repo_url":"https://github.com/aljosaosep/kitti-track-collection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"autonomous-driving","task_name":"Autonomous Driving"},{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-discovery","task_name":"Object Discovery"},{"task_slug":"object-tracking","task_name":"Object Tracking"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1712.08832","atlas_url":"https://app.syntology.ai/?focus=1712.08832","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}