Papers › Adaptive NMS: Refining Pedestrian Detection in a Crowd

Adaptive NMS: Refining Pedestrian Detection in a Crowd

7 Apr 2019CVPR 2019 6arXiv:1904.03629archive 2025-07-28

Songtao Liu, Di Huang, Yunhong Wang

Pedestrian detection in a crowd is a very challenging issue. This paper addresses this problem by a novel Non-Maximum Suppression (NMS) algorithm to better refine the bounding boxes given by detectors. The contributions are threefold: (1) we propose adaptive-NMS, which applies a dynamic suppression threshold to an instance, according to the target density; (2) we design an efficient subnetwork to learn density scores, which can be conveniently embedded into both the single-stage and two-stage detectors; and (3) we achieve state of the art results on the CityPersons and CrowdHuman benchmarks.

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

Object DetectionPedestrian Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Object Detection CrowdHuman (full body) Adaptive NMS (Faster RCNN, ResNet50) AP 84.71 #18 of 19 Archive leaderboard report
Object Detection CrowdHuman (full body) Adaptive NMS (Faster RCNN, ResNet50) mMR 49.73 #18 of 19 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.

Methods

Introduced by this paper: Adaptive NMS

1x1 ConvolutionAdaptive NMSConvolutionDense ConnectionsDropoutFPNFaster R-CNNMax PoolingRPNReLURoIPoolSGD with MomentumSoftmaxStep DecayWeight Decay

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