{"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/qdtrack-quasi-dense-similarity-learning-for","title":"QDTrack: Quasi-Dense Similarity Learning for Appearance-Only Multiple Object Tracking","arxiv_id":"2210.06984","date":"2022-10-12","proceeding":null,"authors":["Tobias Fischer","Thomas E. Huang","Jiangmiao Pang","Linlu Qiu","Haofeng Chen","Trevor Darrell","Fisher Yu"],"abstract":"Similarity learning has been recognized as a crucial step for object tracking. However, existing multiple object tracking methods only use sparse ground truth matching as the training objective, while ignoring the majority of the informative regions in images. In this paper, we present Quasi-Dense Similarity Learning, which densely samples hundreds of object regions on a pair of images for contrastive learning. We combine this similarity learning with multiple existing object detectors to build Quasi-Dense Tracking (QDTrack), which does not require displacement regression or motion priors. We find that the resulting distinctive feature space admits a simple nearest neighbor search at inference time for object association. In addition, we show that our similarity learning scheme is not limited to video data, but can learn effective instance similarity even from static input, enabling a competitive tracking performance without training on videos or using tracking supervision. We conduct extensive experiments on a wide variety of popular MOT benchmarks. We find that, despite its simplicity, QDTrack rivals the performance of state-of-the-art tracking methods on all benchmarks and sets a new state-of-the-art on the large-scale BDD100K MOT benchmark, while introducing negligible computational overhead to the detector.","url_abs":"https://arxiv.org/abs/2210.06984v2","url_pdf":"https://arxiv.org/pdf/2210.06984v2.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":"qdtrack-quasi-dense-similarity-learning-for","repo_url":"https://github.com/SysCV/qdtrack","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"qdtrack-quasi-dense-similarity-learning-for","repo_url":"https://github.com/ethvis/qd-track","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"multiple-object-tracking","task_name":"Multiple Object Tracking"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-tracking","task_name":"Object Tracking"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/multiple-object-tracking-on-bdd100k-test-1","task":"Multiple Object Tracking","dataset":"BDD100K test","model":"QDtrack","rank_in_archive_order":4,"of":5,"metrics":{"mHOTA":"41.8","mIDF1":"52.3","mMOTA":"35.6"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-object-tracking-on-bdd100k-val","task":"Multiple Object Tracking","dataset":"BDD100K val","model":"QDTrack","rank_in_archive_order":4,"of":9,"metrics":{"AssocA":"52.2","TETA":"51.3","mIDF1":"54.3","mMOTA":"42.1"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2210.06984","atlas_url":"https://app.syntology.ai/?focus=2210.06984","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.06984"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/SysCV/qdtrack","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ethvis/qd-track","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":4},"by_repo_kind":{"listed":{"samples":4,"ran":4,"repositories":2}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"70fa1732cf6a9695","entry":"aggregate_accs","repo":"SysCV/qdtrack","repo_kind":"listed","path":"qdtrack/core/evaluation/mot.py","file_url":"https://github.com/SysCV/qdtrack/blob/HEAD/qdtrack/core/evaluation/mot.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"70fa1732cf6a9695"}},{"code_sha256_prefix":"9971851d5c0043b1","entry":"cal_similarity","repo":"ethvis/qd-track","repo_kind":"listed","path":"qdtrack/core/track/similarity.py","file_url":"https://github.com/ethvis/qd-track/blob/HEAD/qdtrack/core/track/similarity.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9971851d5c0043b1"}},{"code_sha256_prefix":"f27f65c4bf0306a0","entry":"restore_result","repo":"ethvis/qd-track","repo_kind":"listed","path":"qdtrack/core/track/transforms.py","file_url":"https://github.com/ethvis/qd-track/blob/HEAD/qdtrack/core/track/transforms.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f27f65c4bf0306a0"}},{"code_sha256_prefix":"0cf0389ba9acbc93","entry":"track2result","repo":"ethvis/qd-track","repo_kind":"listed","path":"qdtrack/core/track/transforms.py","file_url":"https://github.com/ethvis/qd-track/blob/HEAD/qdtrack/core/track/transforms.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0cf0389ba9acbc93"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}