Beta R-CNN: Looking into Pedestrian Detection from Another Perspective

NeurIPS 2020  ·  Zixuan Xu, Banghuai Li, Ye Yuan, Anhong Dang ·

Recently significant progress has been made in pedestrian detection, but it remains challenging to achieve high performance in occluded and crowded scenes. It could be attributed mostly to the widely used representation of pedestrians, i.e., 2D axis-aligned bounding box, which just describes the approximate location and size of the object. Bounding box models the object as a uniform distribution within the boundary, making pedestrians indistinguishable in occluded and crowded scenes due to much noise. To eliminate the problem, we propose a novel representation based on 2D beta distribution, named Beta Representation. It pictures a pedestrian by explicitly constructing the relationship between full-body and visible boxes, and emphasizes the center of visual mass by assigning different probability values to pixels. As a result, Beta Representation is much better for distinguishing highly-overlapped instances in crowded scenes with a new NMS strategy named BetaNMS. What's more, to fully exploit Beta Representation, a novel pipeline Beta R-CNN equipped with BetaHead and BetaMask is proposed, leading to high detection performance in occluded and crowded scenes.

PDF Abstract NeurIPS 2020 PDF NeurIPS 2020 Abstract
No code implementations yet. Submit your code now
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Pedestrian Detection CityPersons Beta R-CNN Reasonable MR^-2 10.6 # 6
Heavy MR^-2 47.1 # 6
Partial MR^-2 10.3 # 4
Bare MR^-2 6.4 # 4
Object Detection CrowdHuman (full body) Beta R-CNN AP 89.6 # 4
mMR 40.3 # 2


No methods listed for this paper. Add relevant methods here