Mutual Distillation Learning For Person Re-Identification

TL;DR

This paper introduces MDPR, a novel person re-identification method that uses mutual distillation between two branches to improve feature extraction from multiple perspectives, achieving state-of-the-art results.

Contribution

The paper proposes a unified model with two branches employing mutual distillation to enhance local and global feature representations for person ReID.

Findings

Achieves 88.7% mAP and 94.4% Rank-1 on DukeMTMC-reID

Outperforms existing state-of-the-art methods

Validates effectiveness through extensive experiments

Abstract

With the rapid advancements in deep learning technologies, person re-identification (ReID) has witnessed remarkable performance improvements. However, the majority of prior works have traditionally focused on solving the problem via extracting features solely from a single perspective, such as uniform partitioning, hard attention mechanisms, or semantic masks. While these approaches have demonstrated efficacy within specific contexts, they fall short in diverse situations. In this paper, we propose a novel approach, Mutual Distillation Learning For Person Re-identification (termed as MDPR), which addresses the challenging problem from multiple perspectives within a single unified model, leveraging the power of mutual distillation to enhance the feature representations collectively. Specifically, our approach encompasses two branches: a hard content branch to extract local features via a uniform horizontal partitioning strategy and a Soft Content Branch to dynamically distinguish between foreground and background and facilitate the extraction of multi-granularity features via a carefully designed attention mechanism. To facilitate knowledge exchange between these two branches, a mutual distillation and fusion process is employed, promoting the capability of the outputs of each branch. Extensive experiments are conducted on widely used person ReID datasets to validate the effectiveness and superiority of our approach. Notably, our method achieves an impressive $88.7\%/94.4\%$ in mAP/Rank-1 on the DukeMTMC-reID dataset, surpassing the current state-of-the-art results. Our source code is available at https://github.com/KuilongCui/MDPR.