Detection in Crowded Scenes: One Proposal, Multiple Predictions

CVPR 2020  ·  Xuangeng Chu, Anlin Zheng, Xiangyu Zhang, Jian Sun ·

We propose a simple yet effective proposal-based object detector, aiming at detecting highly-overlapped instances in crowded scenes. The key of our approach is to let each proposal predict a set of correlated instances rather than a single one in previous proposal-based frameworks. Equipped with new techniques such as EMD Loss and Set NMS, our detector can effectively handle the difficulty of detecting highly overlapped objects. On a FPN-Res50 baseline, our detector can obtain 4.9\% AP gains on challenging CrowdHuman dataset and 1.0\% $\text{MR}^{-2}$ improvements on CityPersons dataset, without bells and whistles. Moreover, on less crowed datasets like COCO, our approach can still achieve moderate improvement, suggesting the proposed method is robust to crowdedness. Code and pre-trained models will be released at

PDF Abstract CVPR 2020 PDF CVPR 2020 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Object Detection CrowdHuman (full body) CrowdDet AP 90.7 # 2
mMR 41.4 # 3
Pedestrian Detection TJU-Ped-campus CrowdDet R (miss rate) 25.73 # 2
RS (miss rate) - # 4
HO (miss rate) 66.38 # 2
R+HO (miss rate) 33.63 # 2
ALL (miss rate) 35.90 # 2
Pedestrian Detection TJU-Ped-traffic CrowdDet R (miss rate) 20.82 # 2
RS (miss rate) - # 4
HO (miss rate) 61.22 # 3
R+HO (miss rate) 25.28 # 2
ALL (miss rate) 36.94 # 2


No methods listed for this paper. Add relevant methods here