# PS-RCNN: Detecting Secondary Human Instances in a Crowd via Primary Object Suppression

arXiv: https://arxiv.org/abs/2003.07080 · HTML: https://mlsanity.com/paper/2003.07080/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Mar 2020.

## Built on by (most cited first, 7 of 7)

- [OTA: Optimal Transport Assignment for Object Detection](https://mlsanity.com/paper/2103.14259/) (2021)
- [Dense Teacher: Dense Pseudo-Labels for Semi-supervised Object Detection](https://mlsanity.com/paper/2207.02541/) (2022)
- [Progressive End-to-End Object Detection in Crowded Scenes](https://mlsanity.com/paper/2203.07669/) (2022)
- [LLA: Loss-aware Label Assignment for Dense Pedestrian Detection](https://mlsanity.com/paper/2101.04307/) (2021)
- [Cross-DINO: Cross the Deep MLP and Transformer for Small Object Detection](https://mlsanity.com/paper/2505.21868/) (2025)
- [DS-Det: Single-Query Paradigm and Attention Disentangled Learning for Flexible Object Detection](https://mlsanity.com/paper/2507.19807/) (2025)
- [Exclusivity-Guided Mask Learning for Semi-Supervised Crowd Instance Segmentation and Counting](https://mlsanity.com/paper/2603.16241/) (2026)

## Abstract (arXiv)

Detecting human bodies in highly crowded scenes is a challenging problem. Two main reasons result in such a problem: 1). weak visual cues of heavily occluded instances can hardly provide sufficient information for accurate detection; 2). heavily occluded instances are easier to be suppressed by Non-Maximum-Suppression (NMS). To address these two issues, we introduce a variant of two-stage detectors called PS-RCNN. PS-RCNN first detects slightly/none occluded objects by an R-CNN module (referred as P-RCNN), and then suppress the detected instances by human-shaped masks so that the features of heavily occluded instances can stand out. After that, PS-RCNN utilizes another R-CNN module specialized in heavily occluded human detection (referred as S-RCNN) to detect the rest missed objects by P-RCNN. Final results are the ensemble of the outputs from these two R-CNNs. Moreover, we introduce a High Resolution RoI Align (HRRA) module to retain as much of fine-grained features of visible parts of the heavily occluded humans as possible. Our PS-RCNN significantly improves recall and AP by 4.49% and 2.92% respectively on CrowdHuman, compared to the baseline. Similar improvements on Widerperson are also achieved by the PS-RCNN.