# Deep Attention Aware Feature Learning for Person Re-Identification

arXiv: https://arxiv.org/abs/2003.00517 · HTML: https://mlsanity.com/paper/2003.00517/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Mar 2020.

## Built on by (most cited first, 8 of 8)

- [Person Re-identification: A Retrospective on Domain Specific Open Challenges and Future Trends](https://mlsanity.com/paper/2202.13121/) (2022)
- [Homogeneous and Heterogeneous Relational Graph for Visible-infrared Person Re-identification](https://mlsanity.com/paper/2109.08811/) (2021)
- [FocusNet: Classifying Better by Focusing on Confusing Classes](https://mlsanity.com/paper/2110.07307/) (2021)
- [BR-NPA: A Non-Parametric High-Resolution Attention Model to improve the Interpretability of Attention](https://mlsanity.com/paper/2106.02566/) (2021)
- [MSCMNet: Multi-scale Semantic Correlation Mining for Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2311.14395/) (2023)
- [Cerberus: Attribute-based person re-identification using semantic IDs](https://mlsanity.com/paper/2412.01048/) (2024)
- [Multilinear subspace learning for person re-identification based fusion of high order tensor features](https://mlsanity.com/paper/2505.15825/) (2025)
- [Differentially Private Cross-camera Person Re-identification](https://mlsanity.com/paper/2306.02765/) (2023)

## Abstract (arXiv)

Visual attention has proven to be effective in improving the performance of person re-identification. Most existing methods apply visual attention heuristically by learning an additional attention map to re-weight the feature maps for person re-identification. However, this kind of methods inevitably increase the model complexity and inference time. In this paper, we propose to incorporate the attention learning as additional objectives in a person ReID network without changing the original structure, thus maintain the same inference time and model size. Two kinds of attentions have been considered to make the learned feature maps being aware of the person and related body parts respectively. Globally, a holistic attention branch (HAB) makes the feature maps obtained by backbone focus on persons so as to alleviate the influence of background. Locally, a partial attention branch (PAB) makes the extracted features be decoupled into several groups and be separately responsible for different body parts (i.e., keypoints), thus increasing the robustness to pose variation and partial occlusion. These two kinds of attentions are universal and can be incorporated into existing ReID networks. We have tested its performance on two typical networks (TriNet and Bag of Tricks) and observed significant performance improvement on five widely used datasets.