Repulsion Loss: Detecting Pedestrians in a Crowd

Detecting individual pedestrians in a crowd remains a challenging problem since the pedestrians often gather together and occlude each other in real-world scenarios. In this paper, we first explore how a state-of-the-art pedestrian detector is harmed by crowd occlusion via experimentation, providing insights into the crowd occlusion problem... Then, we propose a novel bounding box regression loss specifically designed for crowd scenes, termed repulsion loss. This loss is driven by two motivations: the attraction by target, and the repulsion by other surrounding objects. The repulsion term prevents the proposal from shifting to surrounding objects thus leading to more crowd-robust localization. Our detector trained by repulsion loss outperforms all the state-of-the-art methods with a significant improvement in occlusion cases. read more

PDF Abstract CVPR 2018 PDF CVPR 2018 Abstract


Results from the Paper

Ranked #4 on Pedestrian Detection on Caltech (using extra training data)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Result Benchmark
Pedestrian Detection Caltech RepLoss Reasonable Miss Rate 5.0 # 8
Pedestrian Detection Caltech RepLoss + CityPersons dataset Reasonable Miss Rate 4.0 # 4
Pedestrian Detection CityPersons RepLoss Reasonable MR^-2 13.2 # 9
Heavy MR^-2 56.9 # 11
Partial MR^-2 16.8 # 10
Bare MR^-2 7.6 # 8


No methods listed for this paper. Add relevant methods here