Disentanglement-based Cross-Domain Feature Augmentation for Effective Unsupervised Domain Adaptive Person Re-identification
This work addresses domain adaptation for person re-identification, which is incremental as it builds on existing methods to improve sample generation.
The paper tackles the challenge of generating reliable labeled samples for unsupervised domain adaptive person re-identification by proposing a disentanglement-based cross-domain feature augmentation strategy, achieving state-of-the-art performance in experiments.
Unsupervised domain adaptive (UDA) person re-identification (ReID) aims to transfer the knowledge from the labeled source domain to the unlabeled target domain for person matching. One challenge is how to generate target domain samples with reliable labels for training. To address this problem, we propose a Disentanglement-based Cross-Domain Feature Augmentation (DCDFA) strategy, where the augmented features characterize well the target and source domain data distributions while inheriting reliable identity labels. Particularly, we disentangle each sample feature into a robust domain-invariant/shared feature and a domain-specific feature, and perform cross-domain feature recomposition to enhance the diversity of samples used in the training, with the constraints of cross-domain ReID loss and domain classification loss. Each recomposed feature, obtained based on the domain-invariant feature (which enables a reliable inheritance of identity) and an enhancement from a domain specific feature (which enables the approximation of real distributions), is thus an "ideal" augmentation. Extensive experimental results demonstrate the effectiveness of our method, which achieves the state-of-the-art performance.