RLE: A Unified Perspective of Data Augmentation for Cross-Spectral Re-identification

TL;DR

This paper introduces a unified data augmentation framework called RLE for cross-spectral re-identification, modeling modality discrepancies as local linear transformations and enhancing data diversity through novel augmentation strategies.

Contribution

It proposes the Random Linear Enhancement (RLE) strategy, including MRLE and RRLE, to better simulate linear transformations and improve re-identification performance.

Findings

RLE outperforms existing augmentation methods in experiments.

Both MRLE and RRLE effectively enhance model robustness.

RLE shows potential as a general data augmentation tool.

Abstract

This paper makes a step towards modeling the modality discrepancy in the cross-spectral re-identification task. Based on the Lambertain model, we observe that the non-linear modality discrepancy mainly comes from diverse linear transformations acting on the surface of different materials. From this view, we unify all data augmentation strategies for cross-spectral re-identification by mimicking such local linear transformations and categorizing them into moderate transformation and radical transformation. By extending the observation, we propose a Random Linear Enhancement (RLE) strategy which includes Moderate Random Linear Enhancement (MRLE) and Radical Random Linear Enhancement (RRLE) to push the boundaries of both types of transformation. Moderate Random Linear Enhancement is designed to provide diverse image transformations that satisfy the original linear correlations under constrained conditions, whereas Radical Random Linear Enhancement seeks to generate local linear transformations directly without relying on external information. The experimental results not only demonstrate the superiority and effectiveness of RLE but also confirm its great potential as a general-purpose data augmentation for cross-spectral re-identification. The code is available at \textcolor{magenta}{\url{https://github.com/stone96123/RLE}}.