不可靠部分标签学习与递归分离
Unreliable Partial Label Learning with Recursive Separation
AI总结:
提出UPLLRS框架,通过递归分离训练集并利用半监督学习,解决不可靠部分标签学习中真实标签缺失问题,在高不可靠场景下达到最优性能。
摘要:
部分标签学习(PLL)是一种典型的弱监督学习问题,其中每个实例与一个候选标签集相关联,且其中只有一个标签是真实的。然而,假设真实标签始终位于候选标签集中的假设在现实中是不切实际的,因为现实应用中候选标签集的可靠性无法由标注者保证。因此,提出了一种广义的部分标签学习,称为不可靠部分标签学习(UPLL),其中真实标签可能不在候选标签集中。由于不可靠标注带来的挑战,先前的方法在应用于UPLL时性能会显著下降。为解决该问题,我们提出了一种名为不可靠部分标签学习与递归分离(UPLLRS)的两阶段框架。在第一阶段,提出了自适应递归分离策略,将训练集分为可靠子集和不可靠子集。在第二阶段,采用消歧策略逐步识别可靠子集中的真实标签。同时,采用半监督学习方法从不可靠子集中提取有价值的信息。实验结果表明,我们的方法达到了最先进的性能,特别是在高不可靠性情况下。代码和补充材料可在 https://github.com/dhiyu/UPLLRS 获取。
英文摘要:
Partial label learning (PLL) is a typical weakly supervised learning problem in which each instance is associated with a candidate label set, and among which only one is true. However, the assumption that the ground-truth label is always among the candidate label set would be unrealistic, as the reliability of the candidate label sets in real-world applications cannot be guaranteed by annotators. Therefore, a generalized PLL named Unreliable Partial Label Learning (UPLL) is proposed, in which the true label may not be in the candidate label set. Due to the challenges posed by unreliable labeling, previous PLL methods will experience a marked decline in performance when applied to UPLL. To address the issue, we propose a two-stage framework named Unreliable Partial Label Learning with Recursive Separation (UPLLRS). In the first stage, the self-adaptive recursive separation strategy is proposed to separate the training set into a reliable subset and an unreliable subset. In the second stage, a disambiguation strategy is employed to progressively identify the ground-truth labels in the reliable subset. Simultaneously, semi-supervised learning methods are adopted to extract valuable information from the unreliable subset. Our method demonstrates state-of-the-art performance as evidenced by experimental results, particularly in situations of high unreliability. Code and supplementary materials are available at https://github.com/dhiyu/UPLLRS.
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。