Abstract: Partial label learning is a typical weakly supervised learning paradigm in which each training instance is assigned a candidate label set that contains the true label. The goal of partial label learning is to identify the ground-truth label from the candidate set for each instance. In real-world applications, partial label data usually exhibit class imbalance. This makes learning methods based on prediction confidence and label refinement prone to bias and thus degrades classification performance. This issue is more severe in long-tailed scenarios, where head classes dominate the disambiguation process and tail classes are insufficiently learned. Moreover, existing optimal transport–based label refinement methods still suffer from systematic bias in imbalanced scenarios. To address these issues, this paper proposes a method named C2DOT-PLL for long-tailed partial label learning. While preserving the global consistency advantage of optimal transport, the method first employs a dynamic confidence calibration mechanism to alleviate unfair comparisons caused by inconsistent confidence scales across classes and to reduce the impact of class imbalance on instance-level label competition. Then, an unbiased optimal transport scheme is introduced in the pseudo-label refinement stage to correct the systematic bias induced by entropic regularization, thereby producing more accurate pseudo labels. Experiments are conducted on multiple benchmark datasets with different imbalance levels. The results show that, compared with existing partial label learning methods, C2DOT-PLL achieves the best overall classification accuracy.

摘要： 偏标签学习是一类典型的弱监督学习方法，其训练样本被赋予一个包含真实标签的候选标签集合。偏标签学习的目标是在每个样本的候选标签集合中识别其真实标签。在实际应用中，偏标签数据通常呈现类别不平衡特性，使得基于预测置信度和标签细化的学习方法容易产生偏置，进而影响模型的分类性能。尤其是在长尾场景下，头部类往往在标签消歧过程中占据主导地位，尾部类难以获得有效学习。此外，现有基于最优传输的标签细化方法在不平衡场景下仍存在系统性偏置问题。针对上述问题，本文提出了一种面向长尾偏标签学习方法C2DOT-PLL。该方法在保持最优传输全局一致性优势的基础上，首先通过动态样本预测置信度校准机制缓解不同类别预测置信度尺度不一致带来的比较不公平问题，减少类别不平衡对样本级标签竞争的影响；随后，在伪标签细化阶段引入无偏最优传输，对熵正则化最优传输引入的系统性偏差进行修正，从而获得更加准确的伪标签。在多个具有不同平衡程度的基准数据集上对所提出的方法进行实验验证。实验结果表明，与现有偏标签学习方法相比，C2DOT-PLL在总体分类准确性取得了最优性能。