面向行人重识别的互蒸馏学习
Mutual Distillation Learning For Person Re-Identification
AI总结：
本文提出MDPR方法，通过硬内容分支和软内容分支在统一模型中从多视角提取行人特征，并利用互蒸馏与融合提升表示能力，在DukeMTMC-reID上取得领先性能。
摘要：
随着深度学习技术的快速发展，行人重识别（ReID）取得了显著的性能提升。然而，以往大多数工作通常仅从单一视角提取特征来解决问题，例如均匀分区、硬注意力机制或语义掩码。尽管这些方法在特定场景下已证明有效，但在多样化情况下仍存在不足。本文提出了一种新方法——面向行人重识别的互蒸馏学习（简称MDPR），该方法在单个统一模型中从多个视角应对这一具有挑战性的问题，利用互蒸馏的力量共同增强特征表示。具体而言，我们的方法包含两个分支：硬内容分支通过均匀水平分区策略提取局部特征；软内容分支动态区分前景与背景，并通过精心设计的注意力机制促进多粒度特征的提取。为促进这两个分支之间的知识交换，采用了互蒸馏与融合过程，从而提升每个分支输出的能力。我们在广泛使用的行人ReID数据集上进行了大量实验，以验证所提方法的有效性和优越性。值得注意的是，我们的方法在DukeMTMC-reID数据集上取得了令人瞩目的88.7%/94.4%的mAP/Rank-1结果，超越了当前最先进的成果。我们的源代码可在https://github.com/KuilongCui/MDPR获取。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
