1. ABAE: Auxiliary Balanced AutoEncoder for class-imbalanced semi-supervised learning.
- Author
-
Tang, Qianying, Wei, Xiang, Su, Qi, and Zhang, Shunli
- Subjects
- *
MACHINE learning , *CONFIRMATION bias , *SUPERVISED learning , *DATA distribution - Abstract
Semi-supervised learning has achieved extraordinary success in prevalent image-classification benchmarks. However, a class-balanced distribution that differs notably from real-world data distribution is required. In general, models trained under class-imbalanced semi-supervised learning conditions are severely biased towards the majority classes. To address this issue, we propose a novel framework called ABAE by implanting an Auxiliary Balanced AutoEncoder branch into existing semi-supervised learning algorithms. Considering that adaptive feature augmentation for different classes can alleviate confirmation bias, we devise a class-aware reconstruction loss to train the AutoEncoder module. To further smooth the output, we adopt a graph-based label propagation scheme at the end of the AutoEncoder. Extensive experiments on CIFAR-10/100-LT, SVHN-LT and Small ImageNet-127 demonstrate the effectiveness of ABAE. • Propose an Auxiliary Balanced AutoEncoder branch(ABAE) with a class-aware reconstruction loss for CISSL. • Utilize the adaptive feature augmentation for different classes to alleviate the confirmation bias. • Adopt a graph-based label propagation scheme to smooth the output of the ABAE. • Demonstrate the effectiveness of the ABAE through experiments on various imbalanced datasets. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF