Style Normalization and Restitution for Generalizable Person Re-identification
CVPR, pp. 3140-3149, 2020.
Our framework with Style Normalization and Restitution embedded achieves the best performance on both domain generalization and unsupervised domain adaptation ReID
Existing fully-supervised person re-identification (ReID) methods usually suffer from poor generalization capability caused by domain gaps. The key to solving this problem lies in filtering out identity-irrelevant interference and learning domain-invariant person representations. In this paper, we aim to design a generalizable person Re...More
PPT (Upload PPT)