Consistency Regularization with Generative Adversarial Networks for Semi-Supervised Learning
This work addresses a specific limitation in semi-supervised learning for image classification, offering an incremental improvement over existing GAN-based methods.
The paper tackled the problem of Generative Adversarial Networks (GANs) lagging behind non-GAN methods in semi-supervised learning by introducing a composite consistency regularization method, which improved performance to achieve state-of-the-art among GAN-based approaches on SVHN and CIFAR-10 datasets.
Generative Adversarial Networks (GANs) based semi-supervised learning (SSL) approaches are shown to improve classification performance by utilizing a large number of unlabeled samples in conjunction with limited labeled samples. However, their performance still lags behind the state-of-the-art non-GAN based SSL approaches. We identify that the main reason for this is the lack of consistency in class probability predictions on the same image under local perturbations. Following the general literature, we address this issue via label consistency regularization, which enforces the class probability predictions for an input image to be unchanged under various semantic-preserving perturbations. In this work, we introduce consistency regularization into the vanilla semi-GAN to address this critical limitation. In particular, we present a new composite consistency regularization method which, in spirit, leverages both local consistency and interpolation consistency. We demonstrate the efficacy of our approach on two SSL image classification benchmark datasets, SVHN and CIFAR-10. Our experiments show that this new composite consistency regularization based semi-GAN significantly improves its performance and achieves new state-of-the-art performance among GAN-based SSL approaches.