Resolution-invariant Person ReID Based on Feature Transformation and Self-weighted Attention

TL;DR

This paper introduces a novel two-stream network with feature transformation and self-weighted attention modules to achieve resolution-invariant person re-identification, improving accuracy across various datasets.

Contribution

The paper proposes a new resolution-invariant person ReID method using feature transformation and self-weighted attention modules, addressing resolution variability issues.

Findings

Achieves 43.3% Rank-1 accuracy on CAVIAR dataset.

Achieves 83.2% Rank-1 accuracy on MLR-CUHK03 dataset.

Outperforms state-of-the-art methods on five benchmark datasets.

Abstract

Person Re-identification (ReID) is a critical computer vision task which aims to match the same person in images or video sequences. Most current works focus on settings where the resolution of images is kept the same. However, the resolution is a crucial factor in person ReID, especially when the cameras are at different distances from the person or the camera's models are different from each other. In this paper, we propose a novel two-stream network with a lightweight resolution association ReID feature transformation (RAFT) module and a self-weighted attention (SWA) ReID module to evaluate features under different resolutions. RAFT transforms the low resolution features to corresponding high resolution features. SWA evaluates both features to get weight factors for the person ReID. Both modules are jointly trained to get a resolution-invariant representation. Extensive experiments on five benchmark datasets show the effectiveness of our method. For instance, we achieve Rank-1 accuracy of 43.3% and 83.2% on CAVIAR and MLR-CUHK03, outperforming the state-of-the-art.