Mitigating Instance Entanglement in Instance-Dependent Partial Label Learning
This work aims to improve the accuracy of weakly supervised classification for machine learning practitioners by mitigating class confusion in instance-dependent partial label learning, which is an incremental improvement to existing methods.
This paper addresses instance entanglement in instance-dependent partial label learning (ID-PLL), a scenario where candidate labels are influenced by instance features, leading to increased class confusion. The authors propose the Class-specific Augmentation based Disentanglement (CAD) framework, which uses intra- and inter-class regulations to improve class boundary clarity and reduce confusion, demonstrating its effectiveness in enhancing ID-PLL performance.
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.