Multi-Level Attention for Unsupervised Person Re-Identification

TL;DR

This paper introduces a multi-level attention framework for unsupervised person re-identification, combining pixel, head, and domain-level attention to improve feature extraction and identification accuracy.

Contribution

It proposes a novel multi-level attention block that addresses attention spreading and enhances pedestrian feature representation in unsupervised re-identification.

Findings

Improved re-identification accuracy on Market-1501, DukeMTMC-reID, MSMT17, and PersonX datasets.

Effective suppression of attention spreading in unsupervised settings.

Enhanced feature representation through combined multi-level attention.

Abstract

The attention mechanism is widely used in deep learning because of its excellent performance in neural networks without introducing additional information. However, in unsupervised person re-identification, the attention module represented by multi-headed self-attention suffers from attention spreading in the condition of non-ground truth. To solve this problem, we design pixel-level attention module to provide constraints for multi-headed self-attention. Meanwhile, for the trait that the identification targets of person re-identification data are all pedestrians in the samples, we design domain-level attention module to provide more comprehensive pedestrian features. We combine head-level, pixel-level and domain-level attention to propose multi-level attention block and validate its performance on for large person re-identification datasets (Market-1501, DukeMTMC-reID and MSMT17 and PersonX).