Papers › Pedestrian Detection by Exemplar-Guided Contrastive Learning

Pedestrian Detection by Exemplar-Guided Contrastive Learning

17 Nov 2021arXiv:2111.08974archive 2025-07-28

Zebin Lin, Wenjie Pei, Fanglin Chen, David Zhang, Guangming Lu

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.

PaperPDF

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Contrastive LearningPedestrian Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Pedestrian Detection TJU-Ped-campus EGCL ALL (miss rate) 34.87 #1 of 4 Archive leaderboard report
Pedestrian Detection TJU-Ped-campus EGCL HO (miss rate) 65.27 #1 of 4 Archive leaderboard report
Pedestrian Detection TJU-Ped-campus EGCL R (miss rate) 24.84 #1 of 4 Archive leaderboard report
Pedestrian Detection TJU-Ped-campus EGCL R+HO (miss rate) 32.39 #1 of 4 Archive leaderboard report
Pedestrian Detection TJU-Ped-campus EGCL RS (miss rate) - #1 of 4 Archive leaderboard report
Pedestrian Detection TJU-Ped-traffic EGCL ALL (miss rate) 35.76 #2 of 6 Archive leaderboard report
Pedestrian Detection TJU-Ped-traffic EGCL HO (miss rate) 60.05 #2 of 6 Archive leaderboard report
Pedestrian Detection TJU-Ped-traffic EGCL R (miss rate) 19.73 #2 of 6 Archive leaderboard report
Pedestrian Detection TJU-Ped-traffic EGCL R+HO (miss rate) 24.19 #2 of 6 Archive leaderboard report
Pedestrian Detection TJU-Ped-traffic EGCL RS (miss rate) - #2 of 6 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Contrastive Learning

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections