{"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/pedestrian-detection-by-exemplar-guided","title":"Pedestrian Detection by Exemplar-Guided Contrastive Learning","arxiv_id":"2111.08974","date":"2021-11-17","proceeding":null,"authors":["Zebin Lin","Wenjie Pei","Fanglin Chen","David Zhang","Guangming Lu"],"abstract":"Typical methods for pedestrian detection focus on either tackling mutual occlusions between crowded pedestrians, or dealing with the various scales of pedestrians. Detecting pedestrians with substantial appearance diversities such as different pedestrian silhouettes, different viewpoints or different dressing, remains a crucial challenge. Instead of learning each of these diverse pedestrian appearance features individually as most existing methods do, we propose to perform contrastive learning to guide the feature learning in such a way that the semantic distance between pedestrians with different appearances in the learned feature space is minimized to eliminate the appearance diversities, whilst the distance between pedestrians and background is maximized. To facilitate the efficiency and effectiveness of contrastive learning, we construct an exemplar dictionary with representative pedestrian appearances as prior knowledge to construct effective contrastive training pairs and thus guide contrastive learning. Besides, the constructed exemplar dictionary is further leveraged to evaluate the quality of pedestrian proposals during inference by measuring the semantic distance between the proposal and the exemplar dictionary. Extensive experiments on both daytime and nighttime pedestrian detection validate the effectiveness of the proposed method.","url_abs":"https://arxiv.org/abs/2111.08974v3","url_pdf":"https://arxiv.org/pdf/2111.08974v3.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":[],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"pedestrian-detection","task_name":"Pedestrian Detection"}],"methods":[{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/pedestrian-detection-on-tju-ped-campus","task":"Pedestrian Detection","dataset":"TJU-Ped-campus","model":"EGCL","rank_in_archive_order":1,"of":4,"metrics":{"ALL (miss rate)":"34.87","HO (miss rate)":"65.27","R (miss rate)":"24.84","R+HO (miss rate)":"32.39","RS (miss rate)":"-"},"uses_additional_data":false},{"leaderboard":"/sota/pedestrian-detection-on-tju-ped-traffic","task":"Pedestrian Detection","dataset":"TJU-Ped-traffic","model":"EGCL","rank_in_archive_order":2,"of":6,"metrics":{"ALL (miss rate)":"35.76","HO (miss rate)":"60.05","R (miss rate)":"19.73","R+HO (miss rate)":"24.19","RS (miss rate)":"-"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2111.08974","atlas_url":"https://app.syntology.ai/?focus=2111.08974","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}