On Data Augmentation for GAN Training

Abstract

Recent successes in Generative Adversarial Networks (GAN) have affirmed the importance of using more data in GAN training. Yet it is expensive to collect data in many domains such as medical applications. Data Augmentation (DA) has been applied in these applications. In this work, we first argue that the classical DA approach could mislead the generator to learn the distribution of the augmented data, which could be different from that of the original data. We then propose a principled framework, termed Data Augmentation Optimized for GAN (DAG), to enable the use of augmented data in GAN training to improve the learning of the original distribution. We provide theoretical analysis to show that using our proposed DAG aligns with the original GAN in minimizing the Jensen-Shannon (JS) divergence between the original distribution and model distribution. Importantly, the proposed DAG effectively leverages the augmented data to improve the learning of discriminator and generator. We conduct experiments to apply DAG to different GAN models: unconditional GAN, conditional GAN, self-supervised GAN and CycleGAN using datasets of natural images and medical images. The results show that DAG achieves consistent and considerable improvements across these models. Furthermore, when DAG is used in some GAN models, the system establishes state-of-the-art Frechet Inception Distance (FID) scores. Our code is available.

arXiv commentAccepted in IEEE Transactions on Image Processing

References in corpus (5)

• Overcoming catastrophic forgetting in neural networks
• GAN-based Synthetic Medical Image Augmentation for increased CNN Performance in Liver Lesion Classification
• Perceptual Adversarial Networks for Image-to-Image Transformation
• Generative Adversarial Networks and Perceptual Losses for Video Super-Resolution
• The Unusual Effectiveness of Averaging in GAN Training

Cited by in corpus (13)

• A Deep-Learning Intelligent System Incorporating Data Augmentation for Short-Term Voltage Stability Assessment of Power Systems
• Deep learning based on Transformer architecture for power system short-term voltage stability assessment with class imbalance
• A survey on GANs for computer vision: Recent research, analysis and taxonomy
• Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Models
• E2Style: Improve the Efficiency and Effectiveness of StyleGAN Inversion
• PConv: Simple yet Effective Convolutional Layer for Generative Adversarial Network
• Distilling and Transferring Knowledge via cGAN-generated Samples for Image Classification and Regression
• Facial Expression Analysis and Its Potentials in IoT Systems: A Contemporary Survey
• Few-shot Image Generation via Masked Discrimination
• A Flow-Based Model for Conditional and Probabilistic Electricity Consumption Profile Generation and Prediction
• Iterative Framework For Data Augmentation Of Segmented Fingerprints
• A Glimpse of Physical Layer Decision Mechanisms: Facts, Challenges, and Remedies
• HP-GAN: Harnessing pretrained networks for GAN improvement with FakeTwins and discriminator consistency