Domain Adaptive Attention Learning for Unsupervised Person Re-Identification
This addresses the challenge of cross-dataset person re-identification without target annotations, which is incremental as it builds on existing domain adaptation methods.
The paper tackles the problem of unsupervised person re-identification across datasets by proposing a domain adaptive attention learning approach to transfer discriminative representations from labeled to unlabeled domains, achieving state-of-the-art performance on benchmarks like Market-1501, DukeMTMC-reID, and MSMT17.
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.