{"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/contrastive-learning-for-multi-object","title":"Contrastive Learning for Multi-Object Tracking with Transformers","arxiv_id":"2311.08043","date":"2023-11-14","proceeding":null,"authors":["Pierre-François De Plaen","Nicola Marinello","Marc Proesmans","Tinne Tuytelaars","Luc van Gool"],"abstract":"The DEtection TRansformer (DETR) opened new possibilities for object detection by modeling it as a translation task: converting image features into object-level representations. Previous works typically add expensive modules to DETR to perform Multi-Object Tracking (MOT), resulting in more complicated architectures. We instead show how DETR can be turned into a MOT model by employing an instance-level contrastive loss, a revised sampling strategy and a lightweight assignment method. Our training scheme learns object appearances while preserving detection capabilities and with little overhead. Its performance surpasses the previous state-of-the-art by +2.6 mMOTA on the challenging BDD100K dataset and is comparable to existing transformer-based methods on the MOT17 dataset.","url_abs":"https://arxiv.org/abs/2311.08043v1","url_pdf":"https://arxiv.org/pdf/2311.08043v1.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":"contrastive-learning-for-multi-object","repo_url":"https://github.com/pfdp0/ContrasTR","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"multi-object-tracking","task_name":"Multi-Object Tracking"},{"task_slug":"multiple-object-tracking","task_name":"Multiple Object Tracking"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-tracking","task_name":"Object Tracking"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"detr","method_name":"Detr"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"feedforward-network","method_name":"Feedforward Network"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/multi-object-tracking-on-mot17","task":"Multi-Object Tracking","dataset":"MOT17","model":"ContrasTR","rank_in_archive_order":27,"of":48,"metrics":{"HOTA":"58.9","IDF1":"71.8","MOTA":"73.7 "},"uses_additional_data":false},{"leaderboard":"/sota/multiple-object-tracking-on-bdd100k-test-1","task":"Multiple Object Tracking","dataset":"BDD100K test","model":"ContrasTR","rank_in_archive_order":1,"of":5,"metrics":{"mHOTA":"46.1","mIDF1":"56.5","mMOTA":"42.8"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-object-tracking-on-bdd100k-val","task":"Multiple Object Tracking","dataset":"BDD100K val","model":"ContrasTR","rank_in_archive_order":5,"of":9,"metrics":{"AssocA":"-","TETA":"-","mIDF1":"52.9","mMOTA":"41.7"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}