Short range correlation transformer for occluded person re-identification

Abstract

Occluded person re-identification is one of the challenging areas of computer vision, which faces problems such as inefficient feature representation and low recognition accuracy. Recently, vision transformer is introduced into the field of re-identification and achieved state-of-the-art results by constructing global feature relationships between patch sequences. However, vision transformer is not good at capturing short-range correlations of patch sequence and exploiting spatial correlation in patch sequence, which leads to a decrease in the accuracy and robustness of the network in the face of occluded person re-identification. Therefore, to address the above problems, we design a partial feature transformer-based occluded person re-identification framework named PFT. The proposed PFT utilizes three modules to enhance the efficiency of vision transformer. (1) Patch full dimension enhancement module. We design a learnable tensor with the same size as patch sequences, which is full-dimensional and deeply embedded in patch sequences to enrich the diversity of training samples. (2) Fusion and reconstruction module. We extract the less important part of obtained patch sequences, and fuse them with original patch sequence to reconstruct the original patch sequences. (3) Spatial Slicing Module. We slice and group patch sequences from spatial direction, which can effectively improve the short-range correlation of patch sequences. Experimental results over occluded and holistic re-identification datasets demonstrate that the proposed PFT network achieves superior performance consistently and outperforms the state-of-the-art methods.