One-Shot Unsupervised Cross-Domain Person Re-Identification

Cross-domain person re-identification is challenging due to the notorious domain shift problem. Most of the existing unsupervised cross-domain person ReID methods require a large number of unlabeled target-domain samples for adaptation. However, large scale of training data are not always available due to public privacy. Domain generalization methods have inferior adaptation ability without seeing any target domain data. Inspired by the few-shot learning capability of human vision system, we propose a novel setting, one-shot unsupervised cross-domain for person ReID and study the ability of adaptation using the minimum number of image in the target domain during training. Specifically, we first propose a novel Group Normalization (GN) based domain generalizable ReID model. We show that the GN based model could strike a better balance between model discrimination and generalization ability, compared with the Batch Normalization (BN) and Instance Normalization (IN) counterparts, and is more suitable for domain generalizable ReID baseline model. Then besides the supervised feature learning task in the source domain, we introduce two self-supervised learning tasks using the one-shot target domain data to further improve the generalization ability of the ReID model. We carefully design model architecture and perform model training to reduce overfitting to the one-shot target domain. Extensive experiments demonstrate the effectiveness of our approach for one-shot unsupervised cross-domain ReID. Our approach can be extended to few-shot setting and increasing the number of shot up to 1,000 images can steadily increase the performance, which provides practical values to the community.