Regularizing Generative Adversarial Networks under Limited Data
arXiv:2104.03310
Abstract
Recent years have witnessed the rapid progress of generative adversarial networks (GANs). However, the success of the GAN models hinges on a large amount of training data. This work proposes a regularization approach for training robust GAN models on limited data. We theoretically show a connection between the regularized loss and an f-divergence called LeCam-divergence, which we find is more robust under limited training data. Extensive experiments on several benchmark datasets demonstrate that the proposed regularization scheme 1) improves the generalization performance and stabilizes the learning dynamics of GAN models under limited training data, and 2) complements the recent data augmentation methods. These properties facilitate training GAN models to achieve state-of-the-art performance when only limited training data of the ImageNet benchmark is available.
CVPR 2021. Project Page: https://hytseng0509.github.io/lecam-gan Code: https://github.com/google/lecam-gan
References in corpus (18)
- 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
- Self-Attention Generative Adversarial Networks
- Which Training Methods for GANs do actually Converge?
- BEGAN: Boundary Equilibrium Generative Adversarial Networks
- On Convergence and Stability of GANs
- The Numerics of GANs
- Diversity-Sensitive Conditional Generative Adversarial Networks
- Freeze the Discriminator: a Simple Baseline for Fine-Tuning GANs
- Beyond Synthetic Noise: Deep Learning on Controlled Noisy Labels
- Image Augmentations for GAN Training
- Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformation
- Robustness of Conditional GANs to Noisy Labels
- Generative Adversarial Networks for Image and Video Synthesis: Algorithms and Applications
- Towards GAN Benchmarks Which Require Generalization
- Improved Consistency Regularization for GANs
- SimAug: Learning Robust Representations from Simulation for Trajectory Prediction
- In&Out : Diverse Image Outpainting via GAN Inversion