Short Range Correlation Transformer for Occluded Person Re-Identification

TL;DR

This paper introduces PFT, a novel transformer-based framework for occluded person re-identification that enhances local feature extraction and short-range correlation, outperforming existing methods.

Contribution

The paper proposes a partial feature transformer (PFT) with three modules to improve local feature extraction and short-range correlation in occluded person re-identification.

Findings

PFT achieves superior performance on occluded and holistic datasets.

The spatial slicing module improves short-range correlation.

Experimental results outperform state-of-the-art methods.

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. Convolutional neural network pays more attention to the extraction of local features, therefore it is difficult to extract features of occluded pedestrians and the effect is not so satisfied. Recently, vision transformer is introduced into the field of re-identification and achieves the most advanced results by constructing the relationship of global features between patch sequences. However, the performance of vision transformer in extracting local features is inferior to that of convolutional neural network. Therefore, we design a partial feature transformer-based 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.