# Repulsion Loss: Detecting Pedestrians in a Crowd

arXiv: https://arxiv.org/abs/1711.07752 · HTML: https://mlsanity.com/paper/1711.07752/

## Key facts

- Cited by 62 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Nov 2017.

## Built on by (most cited first, 30 of 62)

- [MOSE: A New Dataset for Video Object Segmentation in Complex Scenes](https://mlsanity.com/paper/2302.01872/) (2023)
- [Occluded Video Instance Segmentation: A Benchmark](https://mlsanity.com/paper/2102.01558/) (2021)
- [Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers](https://mlsanity.com/paper/2103.12340/) (2021)
- [Beyond Appearance: a Semantic Controllable Self-Supervised Learning Framework for Human-Centric Visual Tasks](https://mlsanity.com/paper/2303.17602/) (2023)
- [MOSEv2: A More Challenging Dataset for Video Object Segmentation in Complex Scenes](https://mlsanity.com/paper/2508.05630/) (2025)
- [Multiview Detection with Shadow Transformer (and View-Coherent Data Augmentation)](https://mlsanity.com/paper/2108.05888/) (2021)
- [Human De-occlusion: Invisible Perception and Recovery for Humans](https://mlsanity.com/paper/2103.11597/) (2021)
- [Progressive End-to-End Object Detection in Crowded Scenes](https://mlsanity.com/paper/2203.07669/) (2022)
- [Occlusion-Aware Video Object Inpainting](https://mlsanity.com/paper/2108.06765/) (2021)
- [Weakly Aligned Feature Fusion for Multimodal Object Detection](https://mlsanity.com/paper/2204.09848/) (2022)
- [Deep Point Set Resampling via Gradient Fields](https://mlsanity.com/paper/2111.02045/) (2021)
- [VLPD: Context-Aware Pedestrian Detection via Vision-Language Semantic Self-Supervision](https://mlsanity.com/paper/2304.03135/) (2023)
- [ICM-3D: Instantiated Category Modeling for 3D Instance Segmentation](https://mlsanity.com/paper/2108.11771/) (2021)
- [Towards Domain Generalization in Object Detection](https://mlsanity.com/paper/2203.14387/) (2022)
- [YOLO-FaceV2: A Scale and Occlusion Aware Face Detector](https://mlsanity.com/paper/2208.02019/) (2022)
- [MDQE: Mining Discriminative Query Embeddings to Segment Occluded Instances on Challenging Videos](https://mlsanity.com/paper/2303.14395/) (2023)
- [Crowd-SAM: SAM as a Smart Annotator for Object Detection in Crowded Scenes](https://mlsanity.com/paper/2407.11464/) (2024)
- [Variational Pedestrian Detection](https://mlsanity.com/paper/2104.12389/) (2021)
- [Boggart: Towards General-Purpose Acceleration of Retrospective Video Analytics](https://mlsanity.com/paper/2106.15315/) (2021)
- [Revisiting Modality Imbalance In Multimodal Pedestrian Detection](https://mlsanity.com/paper/2302.12589/) (2023)
- [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)
- [OGMN: Occlusion-guided Multi-task Network for Object Detection in UAV Images](https://mlsanity.com/paper/2304.11805/) (2023)
- [LLA: Loss-aware Label Assignment for Dense Pedestrian Detection](https://mlsanity.com/paper/2101.04307/) (2021)
- [Deep Learning based Computer Vision Methods for Complex Traffic Environments Perception: A Review](https://mlsanity.com/paper/2211.05120/) (2022)
- [Occluded Video Instance Segmentation: Dataset and ICCV 2021 Challenge](https://mlsanity.com/paper/2111.07950/) (2021)
- [F2DNet: Fast Focal Detection Network for Pedestrian Detection](https://mlsanity.com/paper/2203.02331/) (2022)
- [Improving Crowded Object Detection via Copy-Paste](https://mlsanity.com/paper/2211.12110/) (2022)
- [KTN: Knowledge Transfer Network for Learning Multi-person 2D-3D Correspondences](https://mlsanity.com/paper/2206.10090/) (2022)
- [Occlusion-Aware Instance Segmentation via BiLayer Network Architectures](https://mlsanity.com/paper/2208.04438/) (2022)

## Abstract (arXiv)

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.