Abstract
Partial label learning is a prominent weakly supervised classification task, where each training instance is ambiguously labeled with a set of candidate labels. In real-world scenarios, candidate labels are often influenced by instance features, leading to the emergence of instance-dependent PLL (ID-PLL), a setting that more accurately reflects this relationship. A significant challenge in ID-PLL is instance entanglement, where instances from similar classes share overlapping features and candidate labels, resulting in increased class confusion. To address this issue, we propose a novel Class-specific Augmentation based Disentanglement (CAD) framework, which tackles instance entanglement by both intra- and inter-class regulations. For intra-class regulation, CAD amplifies class-specific features to generate class-wise augmentations and aligns same-class augmentations across instances. For inter-class regulation, CAD introduces a weighted penalty loss function that applies stronger penalties to more ambiguous labels, encouraging larger inter-class distances. By jointly applying intra- and inter-class regulations, CAD improves the clarity of class boundaries and reduces class confusion caused by entanglement. Extensive experimental results demonstrate the effectiveness of CAD in mitigating the entanglement problem and enhancing ID-PLL performance. The code is available at this https URL.
Abstract (translated)
部分标签学习是一种突出的弱监督分类任务，其中每个训练样本都含糊地标记有一组候选标签。在实际场景中，候选标签通常会受到实例特征的影响，从而导致实例依赖型部分标签学习（ID-PLL）的出现，这种设定更准确地反映了两者之间的关系。ID-PLL的一个重要挑战是实例纠缠，即来自相似类别的实例共享重叠的特征和候选标签，这增加了类别混淆的可能性。为了解决这一问题，我们提出了一种基于特定类别的增强去纠缠框架（CAD），该框架通过类内和类间调节来解决实例纠缠问题。 对于类内调节，CAD放大了每个类别的特有特征以生成针对不同类别的数据增强，并对同一类别中的各个实例进行调整以确保一致性。在类间调节方面，CAD引入了一个加权惩罚损失函数，该函数对更加模糊的标签施加强烈的惩罚，鼓励更大的类间距。 通过同时应用类内和类间的调节机制，CAD框架能够提高类别边界的清晰度，并减少由于纠缠而导致的类别混淆问题。大量的实验结果表明，CAD在缓解纠缠问题以及提升ID-PLL性能方面具有显著效果。代码可在以下链接获取：[此处插入实际的URL地址]。
URL
https://arxiv.org/abs/2603.04825
