Completed Part Transformer for Person Re-Identification

Abstract

Recently, part information of pedestrian images has been demonstrated to be effective for person re-identification (ReID), but the part interaction is ignored when using Transformer to learn long-range dependencies. In this paper, we propose a novel transformer network named Completed Part Transformer (CPT) for person ReID, where we design the part transformer layer to learn the completed part interaction. The part transformer layer includes the intra-part layer and the part-global layer, where they consider long-range dependencies from the aspects of the intra-part interaction and the partglobal interaction, simultaneously. Furthermore, in order to overcome the limitation of fixed number of the patch tokens in the transformer layer, we propose the Adaptive Refined Tokens (ART) module to focus on learning the interaction between the informative patch tokens in the pedestrian image, which improves the discrimination of the pedestrian representation. Extensive experimental results on four person ReID datasets, i.e., MSMT17, Market1501, DukeMTMC-reID and CUHK03, demonstrate that the proposed method achieves a new stateof-the-art performance, e.g., it achieves 68.0% mAP and 84.6% Rank-1 accuracy on MSMT17.

Learning the Meta Feature Transformer for Unsupervised Person Re-Identification

“…Recently, researchers have also begun to use transformers to integrate information across different images, improving discriminative and robust identity representations for supervised Re-ID tasks [17,18], demonstrating significant improvements in feature extraction and model efficiency brought about by transformer technology. However, methods based on transformers have not yet been applied to the task of unsupervised pedestrian re-identification using lightweight networks.…”