通过邻居信息降低跨模态伪标签噪声，提升无监督可见-红外行人重识别效果。
Relieving Universal Label Noise for Unsupervised Visible-Infrared Person Re-Identification by Inferring from Neighbors
- 用邻近样本生成软标签替代硬伪标签，减少标签噪声。
- 在RegDB和SYSU-MM01上达到新最优，mAP提升超过2.5%。
- 适合处理无标注的跨模态行人重识别任务，代码开源可复现。
无监督可见-红外行人重识别（USL-VI-ReID）具有重要研究与应用价值，但因缺乏标注而面临挑战。现有方法虽致力于学习模态不变表征，却常受模态内与跨模态伪标签噪声影响，源于聚类结果不佳与显著模态差异，阻碍有效训练。为此，本文提出一种简单却高效的方法，通过利用邻居信息缓解普遍性标签噪声。具体地，引入邻域引导的通用标签校准（N-ULC）模块，在同质与异质空间中以邻近样本推导的软标签替代显式的硬伪标签，降低噪声。同时，设计邻域引导的动态加权（N-DW）模块，通过抑制不可靠样本影响提升训练稳定性。在RegDB与SYSU-MM01数据集上的大量实验表明，本方法尽管结构简单，仍优于现有USL-VI-ReID方法。源码已公开于：https://github.com/tengxiao14/Neighbor-guided-USL-VI-ReID。
原文摘要 · Abstract (English)
Unsupervised visible-infrared person re-identification (USL-VI-ReID) is of great research and practical significance yet remains challenging due to the absence of annotations. Existing approaches aim to learn modality-invariant representations in an unsupervised setting. However, these methods often encounter label noise within and across modalities due to suboptimal clustering results and considerable modality discrepancies, which impedes effective training. To address these challenges, we propose a straightforward yet effective solution for USL-VI-ReID by mitigating universal label noise using neighbor information. Specifically, we introduce the Neighbor-guided Universal Label Calibration (N-ULC) module, which replaces explicit hard pseudo labels in both homogeneous and heterogeneous spaces with soft labels derived from neighboring samples to reduce label noise. Additionally, we present the Neighbor-guided Dynamic Weighting (N-DW) module to enhance training stability by minimizing the influence of unreliable samples. Extensive experiments on the RegDB and SYSU-MM01 datasets demonstrate that our method outperforms existing USL-VI-ReID approaches, despite its simplicity. The source code is available at: https://github.com/tengxiao14/Neighbor-guided-USL-VI-ReID.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。