# MHSA-Net: Multi-Head Self-Attention Network for Occluded Person Re-Identification

arXiv: https://arxiv.org/abs/2008.04015 · HTML: https://mlsanity.com/paper/2008.04015/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Aug 2020.

## Built on by (most cited first, 13 of 13)

- [Body Part-Based Representation Learning for Occluded Person Re-Identification](https://mlsanity.com/paper/2211.03679/) (2022)
- [AAformer: Auto-Aligned Transformer for Person Re-Identification](https://mlsanity.com/paper/2104.00921/) (2021)
- [Erasing, Transforming, and Noising Defense Network for Occluded Person Re-Identification](https://mlsanity.com/paper/2307.07187/) (2023)
- [Multi-view Information Integration and Propagation for Occluded Person Re-identification](https://mlsanity.com/paper/2311.03828/) (2023)
- [Keypoint Promptable Re-Identification](https://mlsanity.com/paper/2407.18112/) (2024)
- [A Versatile Framework for Multi-scene Person Re-identification](https://mlsanity.com/paper/2403.11121/) (2024)
- [Occluded Person Re-Identification with Deep Learning: A Survey and Perspectives](https://mlsanity.com/paper/2311.00603/) (2023)
- [Deep Learning-based Occluded Person Re-identification: A Survey](https://mlsanity.com/paper/2207.14452/) (2022)
- [Learning Feature Recovery Transformer for Occluded Person Re-identification](https://mlsanity.com/paper/2301.01879/) (2023)
- [Deep Rank-Consistent Pyramid Model for Enhanced Crowd Counting](https://mlsanity.com/paper/2201.04819/) (2022)
- [Diverse Representation Embedding for Lifelong Person Re-Identification](https://mlsanity.com/paper/2403.16003/) (2024)
- [Without Paired Labeled Data: End-to-End Self-Supervised Learning for Drone-view Geo-Localization](https://mlsanity.com/paper/2502.11381/) (2025)
- [DDRN:a Data Distribution Reconstruction Network for Occluded Person Re-Identification](https://mlsanity.com/paper/2410.06600/) (2024)

## Abstract (arXiv)

This paper presents a novel person re-identification model, named Multi-Head Self-Attention Network (MHSA-Net), to prune unimportant information and capture key local information from person images. MHSA-Net contains two main novel components: Multi-Head Self-Attention Branch (MHSAB) and Attention Competition Mechanism (ACM). The MHSAB adaptively captures key local person information, and then produces effective diversity embeddings of an image for the person matching. The ACM further helps filter out attention noise and non-key information. Through extensive ablation studies, we verified that the Multi-Head Self-Attention Branch (MHSAB) and Attention Competition Mechanism (ACM) both contribute to the performance improvement of the MHSA-Net. Our MHSA-Net achieves competitive performance in the standard and occluded person Re-ID tasks.