# Domain Adaptive Attention Learning for Unsupervised Person Re-Identification

arXiv: https://arxiv.org/abs/1905.10529 · HTML: https://mlsanity.com/paper/1905.10529/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 May 2019.

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

- [Learning Disentangled Representation Implicitly via Transformer for Occluded Person Re-Identification](https://mlsanity.com/paper/2107.02380/) (2021)
- [ToAlign: Task-oriented Alignment for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2106.10812/) (2021)
- [Unsupervised Person Re-Identification: A Systematic Survey of Challenges and Solutions](https://mlsanity.com/paper/2109.06057/) (2021)
- [Dual Clustering Co-teaching with Consistent Sample Mining for Unsupervised Person Re-Identification](https://mlsanity.com/paper/2210.03339/) (2022)
- [Camera-aware Style Separation and Contrastive Learning for Unsupervised Person Re-identification](https://mlsanity.com/paper/2112.10089/) (2021)
- [Dual Cluster Contrastive learning for Object Re-Identification](https://mlsanity.com/paper/2112.04662/) (2021)
- [Camera-Incremental Object Re-Identification with Identity Knowledge Evolution](https://mlsanity.com/paper/2305.15909/) (2023)

## Abstract (arXiv)

Person re-identification (Re-ID) across multiple datasets is a challenging task due to two main reasons: the presence of large cross-dataset distinctions and the absence of annotated target instances. To address these two issues, this paper proposes a domain adaptive attention learning approach to reliably transfer discriminative representation from the labeled source domain to the unlabeled target domain. In this approach, a domain adaptive attention model is learned to separate the feature map into domain-shared part and domain-specific part. In this manner, the domain-shared part is used to capture transferable cues that can compensate cross-dataset distinctions and give positive contributions to the target task, while the domain-specific part aims to model the noisy information to avoid the negative transfer caused by domain diversity. A soft label loss is further employed to take full use of unlabeled target data by estimating pseudo labels. Extensive experiments on the Market-1501, DukeMTMC-reID and MSMT17 benchmarks demonstrate the proposed approach outperforms the state-of-the-arts.