Papers › DETR for Crowd Pedestrian Detection

DETR for Crowd Pedestrian Detection

12 Dec 2020arXiv:2012.06785archive 2025-07-28

Matthieu Lin, Chuming Li, Xingyuan Bu, Ming Sun, Chen Lin, Junjie Yan, Wanli Ouyang, Zhidong Deng

Pedestrian detection in crowd scenes poses a challenging problem due to the heuristic defined mapping from anchors to pedestrians and the conflict between NMS and highly overlapped pedestrians. The recently proposed end-to-end detectors(ED), DETR and deformable DETR, replace hand designed components such as NMS and anchors using the transformer architecture, which gets rid of duplicate predictions by computing all pairwise interactions between queries. Inspired by these works, we explore their performance on crowd pedestrian detection. Surprisingly, compared to Faster-RCNN with FPN, the results are opposite to those obtained on COCO. Furthermore, the bipartite match of ED harms the training efficiency due to the large ground truth number in crowd scenes. In this work, we identify the underlying motives driving ED's poor performance and propose a new decoder to address them. Moreover, we design a mechanism to leverage the less occluded visible parts of pedestrian specifically for ED, and achieve further improvements. A faster bipartite match algorithm is also introduced to make ED training on crowd dataset more practical. The proposed detector PED(Pedestrian End-to-end Detector) outperforms both previous EDs and the baseline Faster-RCNN on CityPersons and CrowdHuman. It also achieves comparable performance with state-of-the-art pedestrian detection methods. Code will be released soon.

Paper PDF Code

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

Code

Hatmm/PED-DETR-for-Pedestrian-Detection officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

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

Tasks

Decoder Pedestrian Detection

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

1x1 Convolution Absolute Position Encodings Adam Attention BPE Convolution Dense Connections Detr Dropout FPN Feedforward Network Label Smoothing Layer Normalization Linear Layer Multi-Head Attention Position-Wise Feed-Forward Layer Residual Connection Softmax Transformer

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