Adversarial Learning Based on Global and Local Features for Cross-Modal Person Re-identification

In recent years, a great improvement has been achieved in cross-modal person re-identification (Re-ID) methods based on feature partition. However, many works do not use global and local features jointly to improve the accuracy of person identification. It is an important research topic to fully extract and use global features as well as local features, and effectively reduce modality differences. In this paper, we propose an adversarial learning based on global and local features (ALGL) method. We adopt a two-stream network with partially shared parameters as a feature extraction network to extract visible and infrared feature maps. Local features are obtained through Part-based Convolutional Baseline (PCB) operations on feature maps with the local feature learning module. In the global feature learning module, the average pooling is used to obtain the global features. In order to fully explore the discriminative abilities of local features and global features, hetero-center based triplet loss is designed, which brings features of the same category closer, and features of different categories farther away. At the same time, the adversarial learning module minimizes the modality difference between visible and infrared modalities. Experimental results on the SYSU-MM01 and RegDB datasets show that ALGL outperforms the state-of-the-art solutions.