# Relation-Aware Global Attention for Person Re-identification

arXiv: https://arxiv.org/abs/1904.02998 · HTML: https://mlsanity.com/paper/1904.02998/

## Key facts

- Cited by 124 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Apr 2019.

## Built on by (most cited first, 30 of 124)

- [TransReID: Transformer-based Object Re-Identification](https://mlsanity.com/paper/2102.04378/) (2021)
- [Attention Mechanisms in Computer Vision: A Survey](https://mlsanity.com/paper/2111.07624/) (2021)
- [CLIP-ReID: Exploiting Vision-Language Model for Image Re-Identification without Concrete Text Labels](https://mlsanity.com/paper/2211.13977/) (2022)
- [Generalizable Person Re-identification with Relevance-aware Mixture of Experts](https://mlsanity.com/paper/2105.09156/) (2021)
- [Pose-guided Feature Disentangling for Occluded Person Re-identification Based on Transformer](https://mlsanity.com/paper/2112.02466/) (2021)
- [Learning by Aligning: Visible-Infrared Person Re-identification using Cross-Modal Correspondences](https://mlsanity.com/paper/2108.07422/) (2021)
- [State Space Model for New-Generation Network Alternative to Transformers: A Survey](https://mlsanity.com/paper/2404.09516/) (2024)
- [Lifelong Person Re-Identification via Adaptive Knowledge Accumulation](https://mlsanity.com/paper/2103.12462/) (2021)
- [NFormer: Robust Person Re-identification with Neighbor Transformer](https://mlsanity.com/paper/2204.09331/) (2022)
- [RelationTrack: Relation-aware Multiple Object Tracking with Decoupled Representation](https://mlsanity.com/paper/2105.04322/) (2021)
- [IDM: An Intermediate Domain Module for Domain Adaptive Person Re-ID](https://mlsanity.com/paper/2108.02413/) (2021)
- [GiT: Graph Interactive Transformer for Vehicle Re-identification](https://mlsanity.com/paper/2107.05475/) (2021)
- [Instruct-ReID: A Multi-purpose Person Re-identification Task with Instructions](https://mlsanity.com/paper/2306.07520/) (2023)
- [Deep Frequency Filtering for Domain Generalization](https://mlsanity.com/paper/2203.12198/) (2022)
- [Eliminate Deviation with Deviation for Data Augmentation and a General Multi-modal Data Learning Method](https://mlsanity.com/paper/2101.08533/) (2021)
- [HAT: Hierarchical Aggregation Transformers for Person Re-identification](https://mlsanity.com/paper/2107.05946/) (2021)
- [Image-Specific Information Suppression and Implicit Local Alignment for Text-based Person Search](https://mlsanity.com/paper/2208.14365/) (2022)
- [TransMatcher: Deep Image Matching Through Transformers for Generalizable Person Re-identification](https://mlsanity.com/paper/2105.14432/) (2021)
- [Unsupervised Multi-Source Domain Adaptation for Person Re-Identification](https://mlsanity.com/paper/2104.12961/) (2021)
- [Spatio-Temporal Representation Factorization for Video-based Person Re-Identification](https://mlsanity.com/paper/2107.11878/) (2021)
- [Explainable Person Re-Identification with Attribute-guided Metric Distillation](https://mlsanity.com/paper/2103.01451/) (2021)
- [Deep learning-based person re-identification methods: A survey and outlook of recent works](https://mlsanity.com/paper/2110.04764/) (2021)
- [Learning Domain Invariant Representations for Generalizable Person Re-Identification](https://mlsanity.com/paper/2103.15890/) (2021)
- [Transformer for Object Re-Identification: A Survey](https://mlsanity.com/paper/2401.06960/) (2024)
- [Adaptive Sparse Pairwise Loss for Object Re-Identification](https://mlsanity.com/paper/2303.18247/) (2023)
- [Region Generation and Assessment Network for Occluded Person Re-Identification](https://mlsanity.com/paper/2309.03558/) (2023)
- [Aerial-Ground Person Re-ID](https://mlsanity.com/paper/2303.08597/) (2023)
- [Lifelong Unsupervised Domain Adaptive Person Re-identification with Coordinated Anti-forgetting and Adaptation](https://mlsanity.com/paper/2112.06632/) (2021)
- [Semantic-aware Consistency Network for Cloth-changing Person Re-Identification](https://mlsanity.com/paper/2308.14113/) (2023)
- [Quality-aware Part Models for Occluded Person Re-identification](https://mlsanity.com/paper/2201.00107/) (2022)

## Abstract (arXiv)

For person re-identification (re-id), attention mechanisms have become attractive as they aim at strengthening discriminative features and suppressing irrelevant ones, which matches well the key of re-id, i.e., discriminative feature learning. Previous approaches typically learn attention using local convolutions, ignoring the mining of knowledge from global structure patterns. Intuitively, the affinities among spatial positions/nodes in the feature map provide clustering-like information and are helpful for inferring semantics and thus attention, especially for person images where the feasible human poses are constrained. In this work, we propose an effective Relation-Aware Global Attention (RGA) module which captures the global structural information for better attention learning. Specifically, for each feature position, in order to compactly grasp the structural information of global scope and local appearance information, we propose to stack the relations, i.e., its pairwise correlations/affinities with all the feature positions (e.g., in raster scan order), and the feature itself together to learn the attention with a shallow convolutional model. Extensive ablation studies demonstrate that our RGA can significantly enhance the feature representation power and help achieve the state-of-the-art performance on several popular benchmarks. The source code is available at https://github.com/microsoft/Relation-Aware-Global-Attention-Networks.