# Adaptive NMS: Refining Pedestrian Detection in a Crowd

arXiv: https://arxiv.org/abs/1904.03629 · HTML: https://mlsanity.com/paper/1904.03629/

## Key facts

- Cited by 66 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Apr 2019.

## Built on by (most cited first, 30 of 66)

- [OTA: Optimal Transport Assignment for Object Detection](https://mlsanity.com/paper/2103.14259/) (2021)
- [Occluded Video Instance Segmentation: A Benchmark](https://mlsanity.com/paper/2102.01558/) (2021)
- [Physical Adversarial Attack meets Computer Vision: A Decade Survey](https://mlsanity.com/paper/2209.15179/) (2022)
- [GrooMeD-NMS: Grouped Mathematically Differentiable NMS for Monocular 3D Object Detection](https://mlsanity.com/paper/2103.17202/) (2021)
- [3D Object Detection from Images for Autonomous Driving: A Survey](https://mlsanity.com/paper/2202.02980/) (2022)
- [SOLO: A Simple Framework for Instance Segmentation](https://mlsanity.com/paper/2106.15947/) (2021)
- [Progressive End-to-End Object Detection in Crowded Scenes](https://mlsanity.com/paper/2203.07669/) (2022)
- [Real-time Object Detection for Streaming Perception](https://mlsanity.com/paper/2203.12338/) (2022)
- [Relation DETR: Exploring Explicit Position Relation Prior for Object Detection](https://mlsanity.com/paper/2407.11699/) (2024)
- [VLPD: Context-Aware Pedestrian Detection via Vision-Language Semantic Self-Supervision](https://mlsanity.com/paper/2304.03135/) (2023)
- [Boosting Detection in Crowd Analysis via Underutilized Output Features](https://mlsanity.com/paper/2308.16187/) (2023)
- [Crowd-SAM: SAM as a Smart Annotator for Object Detection in Crowded Scenes](https://mlsanity.com/paper/2407.11464/) (2024)
- [You Should Look at All Objects](https://mlsanity.com/paper/2207.07889/) (2022)
- [ODAM: Gradient-based instance-specific visual explanations for object detection](https://mlsanity.com/paper/2304.06354/) (2023)
- [FAQ: Feature Aggregated Queries for Transformer-based Video Object Detectors](https://mlsanity.com/paper/2303.08319/) (2023)
- [Variational Pedestrian Detection](https://mlsanity.com/paper/2104.12389/) (2021)
- [BlockCopy: High-Resolution Video Processing with Block-Sparse Feature Propagation and Online Policies](https://mlsanity.com/paper/2108.09376/) (2021)
- [Pedestrian Detection: Domain Generalization, CNNs, Transformers and Beyond](https://mlsanity.com/paper/2201.03176/) (2022)
- [Beta R-CNN: Looking into Pedestrian Detection from Another Perspective](https://mlsanity.com/paper/2210.12758/) (2022)
- [LLA: Loss-aware Label Assignment for Dense Pedestrian Detection](https://mlsanity.com/paper/2101.04307/) (2021)
- [NMS-Loss: Learning with Non-Maximum Suppression for Crowded Pedestrian Detection](https://mlsanity.com/paper/2106.02426/) (2021)
- [Occluded Video Instance Segmentation: Dataset and ICCV 2021 Challenge](https://mlsanity.com/paper/2111.07950/) (2021)
- [Contrastive Object Detection Using Knowledge Graph Embeddings](https://mlsanity.com/paper/2112.11366/) (2021)
- [PointNeuron: 3D Neuron Reconstruction via Geometry and Topology Learning of Point Clouds](https://mlsanity.com/paper/2210.08305/) (2022)
- [Improving Crowded Object Detection via Copy-Paste](https://mlsanity.com/paper/2211.12110/) (2022)
- [Body-Part Joint Detection and Association via Extended Object Representation](https://mlsanity.com/paper/2212.07652/) (2022)
- [DEYO: DETR with YOLO for Step-by-Step Object Detection](https://mlsanity.com/paper/2211.06588/) (2022)
- [IoU-Enhanced Attention for End-to-End Task Specific Object Detection](https://mlsanity.com/paper/2209.10391/) (2022)
- [DEYOv2: Rank Feature with Greedy Matching for End-to-End Object Detection](https://mlsanity.com/paper/2306.09165/) (2023)
- [Fuzzy-NMS: Improving 3D Object Detection with Fuzzy Classification in NMS](https://mlsanity.com/paper/2310.13951/) (2023)

## Abstract (arXiv)

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.