Image Augmentations for GAN Training

Abstract

Data augmentations have been widely studied to improve the accuracy and robustness of classifiers. However, the potential of image augmentation in improving GAN models for image synthesis has not been thoroughly investigated in previous studies. In this work, we systematically study the effectiveness of various existing augmentation techniques for GAN training in a variety of settings. We provide insights and guidelines on how to augment images for both vanilla GANs and GANs with regularizations, improving the fidelity of the generated images substantially. Surprisingly, we find that vanilla GANs attain generation quality on par with recent state-of-the-art results if we use augmentations on both real and generated images. When this GAN training is combined with other augmentation-based regularization techniques, such as contrastive loss and consistency regularization, the augmentations further improve the quality of generated images. We provide new state-of-the-art results for conditional generation on CIFAR-10 with both consistency loss and contrastive loss as additional regularizations.

References in corpus (6)

• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• Improved Regularization of Convolutional Neural Networks with Cutout
• Temporal Ensembling for Semi-Supervised Learning
• Amortised MAP Inference for Image Super-resolution
• High-Fidelity Image Generation With Fewer Labels
• Adversarial AutoAugment

Cited by in corpus (9)

• Data-Efficient Instance Generation from Instance Discrimination
• Graph Generative Adversarial Networks for Sparse Data Generation in High Energy Physics
• Regularizing Generative Adversarial Networks under Limited Data
• JOKR: Joint Keypoint Representation for Unsupervised Cross-Domain Motion Retargeting
• Temporal-Aware Self-Supervised Learning for 3D Hand Pose and Mesh Estimation in Videos
• MVHM: A Large-Scale Multi-View Hand Mesh Benchmark for Accurate 3D Hand Pose Estimation
• Improving Augmentation and Evaluation Schemes for Semantic Image Synthesis
• Functional Space Analysis of Local GAN Convergence
• ReMix: Towards Image-to-Image Translation with Limited Data