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 (16)

• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• A Simple Framework for Contrastive Learning of Visual Representations
• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• Large Scale GAN Training for High Fidelity Natural Image Synthesis
• Improved Regularization of Convolutional Neural Networks with Cutout
• Self-Attention Generative Adversarial Networks
• FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence
• Unsupervised Data Augmentation for Consistency Training
• Temporal Ensembling for Semi-Supervised Learning
• Momentum Contrast for Unsupervised Visual Representation Learning
• Self-training with Noisy Student improves ImageNet classification
• Amortised MAP Inference for Image Super-resolution
• Hierarchical Implicit Models and Likelihood-Free Variational Inference
• High-Fidelity Image Generation With Fewer Labels
• Adversarial AutoAugment
• Improved Consistency Regularization for GANs

Cited by in corpus (28)

• Differentiable Augmentation for Data-Efficient GAN Training
• ViTGAN: Training GANs with Vision Transformers
• Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Models
• A Good Image Generator Is What You Need for High-Resolution Video Synthesis
• A Systematic Survey of Regularization and Normalization in GANs
• Dataset Condensation with Differentiable Siamese Augmentation
• Cross-Modal Contrastive Learning for Text-to-Image Generation
• Data-Efficient Instance Generation from Instance Discrimination
• PConv: Simple yet Effective Convolutional Layer for Generative Adversarial Network
• Deceive D: Adaptive Pseudo Augmentation for GAN Training with Limited Data
• Improved Consistency Regularization for GANs
• Distilling and Transferring Knowledge via cGAN-generated Samples for Image Classification and Regression
• Making Invisible Visible: Data-Driven Seismic Inversion with Spatio-temporally Constrained Data Augmentation
• Graph Generative Adversarial Networks for Sparse Data Generation in High Energy Physics
• Top-k Training of GANs: Improving GAN Performance by Throwing Away Bad Samples
• Regularizing Generative Adversarial Networks under Limited Data
• Few-shot Image Generation via Masked Discrimination
• Continuous Conditional Generative Adversarial Networks: Novel Empirical Losses and Label Input Mechanisms
• One-Shot Generative Domain Adaptation
• Self-Supervised GANs with Label Augmentation
• Dual Contrastive Loss and Attention for GANs
• 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
• Exploiting Chain Rule and Bayes' Theorem to Compare Probability Distributions
• Functional Space Analysis of Local GAN Convergence
• ReMix: Towards Image-to-Image Translation with Limited Data