Unsupervised Visible-Infrared Person ReID by Collaborative Learning with Neighbor-Guided Label Refinement

TL;DR

This paper introduces a novel unsupervised learning framework for visible-infrared person re-identification that effectively addresses cross-modality data association and label noise, significantly improving performance over existing methods.

Contribution

The paper proposes the DOTLA framework with neighbor-guided label refinement, a new approach for cross-modality data association and noise reduction in unsupervised VI-ReID.

Findings

Achieves 7.76% higher mAP on SYSU-MM01 dataset.

Surpasses some supervised VI-ReID methods.

Demonstrates robustness to noisy labels.

Abstract

Unsupervised learning visible-infrared person re-identification (USL-VI-ReID) aims at learning modality-invariant features from unlabeled cross-modality dataset, which is crucial for practical applications in video surveillance systems. The key to essentially address the USL-VI-ReID task is to solve the cross-modality data association problem for further heterogeneous joint learning. To address this issue, we propose a Dual Optimal Transport Label Assignment (DOTLA) framework to simultaneously assign the generated labels from one modality to its counterpart modality. The proposed DOTLA mechanism formulates a mutual reinforcement and efficient solution to cross-modality data association, which could effectively reduce the side-effects of some insufficient and noisy label associations. Besides, we further propose a cross-modality neighbor consistency guided label refinement and regularization module, to eliminate the negative effects brought by the inaccurate supervised signals, under the assumption that the prediction or label distribution of each example should be similar to its nearest neighbors. Extensive experimental results on the public SYSU-MM01 and RegDB datasets demonstrate the effectiveness of the proposed method, surpassing existing state-of-the-art approach by a large margin of 7.76% mAP on average, which even surpasses some supervised VI-ReID methods.