Person Re-identification with a Cloth-Changing Aware Transformer
Xuena Ren, Dongming Zhang, Xiuguo Bao · 2022 International Joint Conference on Neural Networks (IJCNN) · 2022
Cloth-Changing person re-identification is a challenging problem for its huge intra-class variance caused by changing clothes. In this paper, we focus on learning cloth-insensitive features without any cues from external models. Specifically, we introduce a novel Cloth-Changing Aware Transformer(CCAT) to learn identity-relevant cues. The transformer encoder utilizes Cloth Information Embedding(CIE) to encode outfits information and automatically focuses on the identity-discriminative feature. The tokens from the transformer encoder are then fed to the Cloth-Insensitive Consistency Learning(CICL) decoder to learn cloth-irrelevant features from pairwise pedestrian images. Besides, we impose Intra-class Constraint Learning(ICL) to pull the global tokens from the encoder closer. In this way, the model learns the identity-relevant and cloth-insensitive features. Extensive experimental results on three cloth-changing person ReID datasets demonstrate that our proposed algorithm can extract highly robust feature representations of cloth-changing persons, and it outperforms the state-of-the-art cloth-changing person ReID approaches. Our method achieves 87.4% and 69.7% on R-1 accuracy on the latest released LTCC [28] and PRCC [40], which outperforms previous methods with a large margin. The code is available at CCAT.