NOH-NMS: Improving Pedestrian Detection by Nearby Objects Hallucination

The offical implementation for the “NOH-NMS: Improving Pedestrian Detection by Nearby Objects Hallucination” which is published in ACM MM 2020.

We propose Nearby Objects Hallucinator (NOH), which pinpoints the objects nearby each proposal with a Gaussian distribution, together with NOH-NMS, which dynamically eases the suppression for the space that might contain other objects with a high likelihood.

This work has won the first place at the CrowdHuman Challenge, 2020.


Model Backbone AP Recall MR Weights
Faster RCNN ResNet-50 85.0 87.5 44.5 faster_rcnn_model_final.pth
NOH-NMS ResNet-50 88.8 92.6 43.7 noh_nms_model_final.pth

Prepare Datasets

Download the CrowdHuman Datasets from, and then move them under the directory like:

├── annotations
│   └── annotation_train.odgt
│   └── annotation_val.odgt
├── images
│   └── train
│   └── val


  cd detectron2
  pip install -e . 
  #or rebuild

Quick Start

See in detectron2



if you find this project useful for your research, please cite:

  title={NOH-NMS: Improving Pedestrian Detection by Nearby Objects Hallucination},
  author={Zhou, Penghao and Zhou, Chong and Peng, Pai and Du, Junlong and Sun, Xing and Guo, Xiaowei and Huang, Feiyue},
  booktitle={Proceedings of the 28th ACM International Conference on Multimedia},