Learning Progressive Modality-Shared Transformers for Effective Visible-Infrared Person Re-identification

Visible-Infrared Person Re-Identification (VI-ReID) is a challenging retrieval task under complex modality changes. Existing methods usually focus on extracting discriminative visual features while ignoring the reliability and commonality of between different modalities. In this paper, we propose novel deep learning framework named Progressive Modality-shared Transformer (PMT) for effective VI-ReID. To reduce negative effect gaps, first take gray-scale images as an auxiliary progressive strategy. Then, Modality-Shared Enhancement Loss (MSEL) to guide model explore more reliable identity information from modality-shared features. Finally, cope with problem large intra-class differences small inter-class differences, Discriminative Center (DCL) combined MSEL further improve discrimination Extensive experiments SYSU-MM01 RegDB datasets show that our proposed performs better than most state-of-the-art methods. For reproduction, release source code at https://github.com/hulu88/PMT.