Learning Deep Representations by Mutual Information for Person Re-identification

TL;DR

This paper introduces a Deep InfoMax (DIM) network that maximizes mutual information between input images and encoder outputs to improve person re-identification, achieving state-of-the-art results without auxiliary labels.

Contribution

It proposes a novel DIM network for person ReID that enhances feature representations by maximizing mutual information without needing extra labels.

Findings

Achieves state-of-the-art ReID performance.

Effective in cross-dataset unsupervised scenarios.

Demonstrates the benefit of MI maximization in ReID.

Abstract

Most existing person re-identification (ReID) methods have good feature representations to distinguish pedestrians with deep convolutional neural network (CNN) and metric learning methods. However, these works concentrate on the similarity between encoder output and ground-truth, ignoring the correlation between input and encoder output, which affects the performance of identifying different pedestrians. To address this limitation, We design a Deep InfoMax (DIM) network to maximize the mutual information (MI) between the input image and encoder output, which doesn't need any auxiliary labels. To evaluate the effectiveness of the DIM network, we propose end-to-end Global-DIM and Local-DIM models. Additionally, the DIM network provides a new solution for cross-dataset unsupervised ReID issue as it needs no extra labels. The experiments prove the superiority of MI theory on the ReID issue, which achieves the state-of-the-art results.