缓解实例依赖偏标签学习中的实例纠缠
Mitigating Instance Entanglement in Instance-Dependent Partial Label Learning
针对弱监督分类中候选标签与实例特征耦合导致的类间混淆，提出类特定增强与加权惩罚损失来拉开类间距离，可复用于噪声标签、开放词表等标签歧义场景下的表征判别性提升。
原文依据 we propose a novel Class-specific Augmentation based Disentanglement (CAD) framework
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论偏标签学习是一种重要的弱监督分类任务，其中每个训练实例都被一组候选标签模糊地标注。在真实场景中，候选标签往往受到实例特征的影响，由此产生了实例依赖偏标签学习（ID-PLL），这一设定更准确地反映了这种关系。ID-PLL 中的一个显著挑战是实例纠缠，即来自相似类别的实例共享重叠的特征与候选标签，从而导致类别混淆加剧。为解决该问题，我们提出了一种新的基于类特定增强的解缠（CAD）框架，它通过类内与类间两种约束来处理实例纠缠。在类内约束方面，CAD 放大类特定特征以生成按类别的增强，并在不同实例之间对齐同类增强。在类间约束方面，CAD 引入加权惩罚损失函数，对更模糊的标签施加更强的惩罚，从而促使类间距离增大。通过联合施加类内与类间约束，CAD 提升了类别边界的清晰度，并减少了由纠缠引起的类别混淆。大量实验结果表明，CAD 在缓解纠缠问题和提升 ID-PLL 性能方面是有效的。代码可在 https://github.com/RyanZhaoIc/CAD.git 获取。
英文原文摘要 1431 字符
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 https://github.com/RyanZhaoIc/CAD.git.