Unsupervised person re-identification (ReID), including fully unsupervised ReID and unsupervised domain adaptive ReID, remains a challenge for the fields of biometrics and computer vision due to its difficulty in learning with unlabeled target domain data. Existing state-of-the-art methods, most of which generate pseudo-labels via unsupervised clustering for model optimization, are inevitably hampered by the under-explored problem of pseudo-label noise. Motivated by this, we propose a novel joint framework termed pseudo-label Noise Prevention, Suppression, and Softening (NPSS) for unsupervised person re-identification. Instead of refining generated label noise after clustering as many existing methods do, we start solving this issue from the source of pseudo-label noise by proposing a new Dynamic Camera-Adaptive Clustering (DCAC), which dynamically involves camera information to prevent noise caused by cross-camera variance, thus improving their quality during clustering. Moreover, we propose an Online Domain Union (ODU) mechanism for the classification model learning on the target domain via involving source domain data with their ground-truth labels, which effectively suppresses the indelible noisy pseudo-labels. Furthermore, we present the Self-Consistency Constraint (SCC) to soften the label noise in a single model with reduced computation and network parameter cost, which achieves intra-sample knowledge ensembling with our global-local SCC and cross-sample knowledge ensembling with our inter-instance SCC. Experiments demonstrate the effectiveness of our method as it surpasses state-of-the-art methods by a large margin on Market-1501, DukeMTMC-ReID, and MSMT17 benchmarks. The code is available at https://github.com/hjwang-824/NPSS .

中文翻译：

---

用于无人监督人员重识别的伪标签噪声预防、抑制和软化

无监督行人再识别 (ReID)，包括完全无监督 ReID 和无监督域自适应 ReID，由于难以使用未标记的目标域数据进行学习，因此仍然是生物识别和计算机视觉领域的一个挑战。现有的最先进方法，其中大部分通过无监督聚类生成伪标签以进行模型优化，不可避免地受到伪标签噪声未充分探索的问题的阻碍。受此启发，我们提出了一种新的联合框架，称为伪标签噪声预防、抑制和软化 (NPSS)，用于无人监督的人员重新识别。我们没有像许多现有方法那样在聚类后细化生成的标签噪声，而是通过提出一种新的动态相机自适应聚类（DCAC）从伪标签噪声的来源开始解决这个问题，它动态地涉及相机信息以防止由跨相机方差引起的噪声，从而提高它们在聚类过程中的质量。此外，我们提出了一种在线域联合 (ODU) 机制，通过将源域数据与它们的真实标签结合起来，在目标域上学习分类模型，有效地抑制了不可磨灭的噪声伪标签。此外，我们提出了自一致性约束（SCC）来软化单个模型中的标签噪声，同时减少计算和网络参数成本，从而实现样本内知识与我们的全局-局部 SCC 集成以及跨样本知识与我们的集成实例间 SCC。实验证明了我们方法的有效性，因为它在 Market-1501、DukeMTMC-ReID、和 MSMT17 基准。该代码可在https://github.com/hjwang-824/NPSS .