TCMM: 面向无监督行人重识别的对比学习Token约束与多尺度记忆库
TCMM: Token Constraint and Multi-Scale Memory Bank of Contrastive Learning for Unsupervised Person Re-identification
AI总结：
针对无监督行人重识别中的块噪声、特征不一致及离群样本浪费问题，提出带Token约束与多尺度记忆库的TCMM方法，在常用基准上取得SOTA性能。
摘要：
本文提出ViT Token约束与多尺度记忆库（TCMM）方法，以解决无监督行人重识别研究中的块噪声与特征不一致问题。许多优秀方法利用ViT特征获取伪标签与聚类原型，再通过对比学习训练模型。然而，ViT通过执行块嵌入处理图像，不可避免地会在块中引入噪声，可能损害重识别模型的性能。另一方面，以往基于记忆库的对比方法受限于批量大小，可能导致数据不一致。此外，现有伪标签方法往往会丢弃难以聚类的离群样本，牺牲了离群样本的潜在价值，导致模型多样性与鲁棒性受限。本文引入ViT Token约束，以减轻块噪声对ViT架构造成的损害。所提出的多尺度记忆库增强了对离群样本的挖掘，并维持特征一致性。实验结果表明，本文系统在常用基准上取得了当前最优性能。该项目可在https://github.com/andy412510/TCMM 获取。
英文摘要：
This paper proposes the ViT Token Constraint and Multi-scale Memory bank (TCMM) method to address the patch noises and feature inconsistency in unsupervised person re-identification works. Many excellent methods use ViT features to obtain pseudo labels and clustering prototypes, then train the model with contrastive learning. However, ViT processes images by performing patch embedding, which inevitably introduces noise in patches and may compromise the performance of the re-identification model. On the other hand, previous memory bank based contrastive methods may lead data inconsistency due to the limitation of batch size. Furthermore, existing pseudo label methods often discard outlier samples that are difficult to cluster. It sacrifices the potential value of outlier samples, leading to limited model diversity and robustness. This paper introduces the ViT Token Constraint to mitigate the damage caused by patch noises to the ViT architecture. The proposed Multi-scale Memory enhances the exploration of outlier samples and maintains feature consistency. Experimental results demonstrate that our system achieves state-of-the-art performance on common benchmarks. The project is available at \href{https://github.com/andy412510/TCMM}{https://github.com/andy412510/TCMM}.
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。
