arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.23133cs.CV

从校准到细化：通过概率证据传播在噪声标签人重识别中寻求确定性

From Calibration to Refinement: Seeking Certainty via Probabilistic Evidence Propagation for Noisy-Label Person Re-Identification

School of Computer Science and Technology, Wuhan University of Science and Technology（武汉科技大学计算机科学与技术学院）；Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System, Wuhan University of Science and Technology（湖北省智能信息处理与实时工业系统重点实验室）；School of Computer Science, Wuhan University（武汉大学计算机学院）；Department of Electrical Engineering and the Institute of Communications Engineering, National Tsing Hua University（清华大学电子工程系和通信工程研究所）；Electronic and Optoelectronic System Research Laboratories, Industrial Technology Research Institute（工业技术研究院电子与光电子系统研究实验室）

Xin Yuan, Zhiyong Zhang, Xin Xu, Zheng Wang, Chia-Wen Lin

备注：
Accepted by IEEE TMM 2026
阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

CARE方法通过概率证据传播解决噪声标签人重识别中的校准与细化问题，提升模型鲁棒性与准确性。

摘要：

随着对在无约束环境中鲁棒性人重识别需求的增加，学习包含噪声标签和稀疏身份样本的数据集仍然是一个关键挑战。现有的噪声鲁棒人重识别方法主要依赖于使用softmax输出的损失校正或样本选择策略。然而，这些方法有两个关键限制：1）Softmax具有平移不变性，导致在损坏标签上产生过于自信且不可靠的预测。2）基于小损失标准的传统样本选择往往丢弃了有价值的难正样本，这些样本对于学习判别特征至关重要。为克服这些问题，我们提出了CAlibration-to-REfinement（CARE）方法，一种两阶段框架，通过从校准到细化的概率证据传播来寻求确定性。在校准阶段，我们提出了概率证据校准（PEC），通过将自适应可学习参数注入相似性函数来破坏softmax的平移不变性，并采用证据校准损失来缓解对错误标记样本的过度自信。在细化阶段，我们设计了证据传播细化（EPR），可以更准确地区分干净和噪声样本。具体来说，EPR包含两个步骤：首先，提出了复合角边距（CAM）度量，以在超球体空间中精确区分干净但难以学习的正样本和错误标记的样本；其次，开发了以确定性为导向的球体加权（COSW），以根据CAM动态分配样本的重要性，确保干净的实例驱动模型更新。在Market1501、DukeMTMC-ReID和CUHK03数据集上，针对随机和模式噪声的大量实验结果表明，CARE实现了具有竞争力的性能。

英文摘要：

With the increasing demand for robust person Re-ID in unconstrained environments, learning from datasets with noisy labels and sparse per-identity samples remains a critical challenge. Existing noise-robust person Re-ID methods primarily rely on loss-correction or sample-selection strategies using softmax outputs. However, these methods suffer from two key limitations: 1) Softmax exhibits translation invariance, leading to over-confident and unreliable predictions on corrupted labels. 2) Conventional sample selection based on small-loss criteria often discards valuable hard positives that are crucial for learning discriminative features. To overcome these issues, we propose the CAlibration-to-REfinement (CARE) method, a two-stage framework that seeks certainty through probabilistic evidence propagation from calibration to refinement. In the calibration stage, we propose the probabilistic evidence calibration (PEC) that dismantles softmax translation invariance by injecting adaptive learnable parameters into the similarity function, and employs an evidential calibration loss to mitigate overconfidence on mislabeled samples. In the refinement stage, we design the evidence propagation refinement (EPR) that can more accurately distinguish between clean and noisy samples. Specifically, the EPR contains two steps: Firstly, the composite angular margin (CAM) metric is proposed to precisely distinguish clean but hard-to-learn positive samples from mislabeled ones in a hyperspherical space; Secondly, the certainty-oriented sphere weighting (COSW) is developed to dynamically allocate the importance of samples according to CAM, ensuring clean instances drive model updates. Extensive experimental results on Market1501, DukeMTMC-ReID, and CUHK03 datasets under both random and patterned noises show that CARE achieves competitive performance.

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。

↑