Multi-Biometric Unified Network for Cloth-Changing Person Re-Identification

Abstract

Person re-identification (re-ID) aims at matching the same person across different cameras. Most of the existing meth-ods for re- ID assume that people wear the same clothes on different cameras. However, Cloth-Changing re- ID is a quite challenging problem since people are likely to change clothes as the time span increases. To tackle this problem, a Multi-Biometric Unified Network (MBUNet) is proposed to ex-ploit clothing-unrelated cues. We firstly introduce a multi-biological feature branch that aims at extracting a variety of biological features, such as the head, neck, and shoulders to resist clothing changes. To extract discriminative fine-grained biological features, we embed a differential feature attention module (DFAM) for it. Besides, we adopt differ-ential recombination on max pooling (DRMP) and apply a direction-adaptive graph convolutional layer to extract more robust global features and pose features. Extensive experi-ments on three Cloth-Changing re-ID datasets show the ad-vantages of our proposed MBUNet.