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

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

23 Oct 2022NeurIPS 2020 12arXiv:2210.12758archive 2025-07-28

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.

PaperPDFConference PDF

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

Pedestrian Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Object Detection CrowdHuman (full body) Beta R-CNN AP 89.6 #12 of 19 Archive leaderboard report
Object Detection CrowdHuman (full body) Beta R-CNN mMR 40.3 #12 of 19 Archive leaderboard report
Pedestrian Detection CityPersons Beta R-CNN Bare MR^-2 6.4 #11 of 22 Archive leaderboard report
Pedestrian Detection CityPersons Beta R-CNN Heavy MR^-2 47.1 #11 of 22 Archive leaderboard report
Pedestrian Detection CityPersons Beta R-CNN Partial MR^-2 10.3 #11 of 22 Archive leaderboard report
Pedestrian Detection CityPersons Beta R-CNN Reasonable MR^-2 10.6 #11 of 22 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.

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