Consistency Regularization with Generative Adversarial Networks for Semi-Supervised Learning

Abstract

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.

arXiv comment9 pages, 5 figures

References in corpus (17)

• Adam: A Method for Stochastic Optimization
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• mixup: Beyond Empirical Risk Minimization
• Stochastic Backpropagation and Approximate Inference in Deep Generative Models
• Temporal Ensembling for Semi-Supervised Learning
• Improved Techniques for Training GANs
• Interpolation Consistency Training for Semi-Supervised Learning
• Adversarially Learned Inference
• Good Semi-supervised Learning that Requires a Bad GAN
• Triple Generative Adversarial Nets
• ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring
• Neural network-based clustering using pairwise constraints
• Learning by Association - A versatile semi-supervised training method for neural networks
• Improving the Improved Training of Wasserstein GANs: A Consistency Term and Its Dual Effect
• Semi-Supervised Learning via Compact Latent Space Clustering
• Manifold regularization with GANs for semi-supervised learning
• Local Clustering with Mean Teacher for Semi-supervised Learning