Regularizing Generative Adversarial Networks under Limited Data

By Hung-Yu Tseng, Lu Jiang, Ce Liu, Ming-Hsuan Yang, Weilong Yang. 2021

185 citations recorded by the source corpus.

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-theart performance when only limited training data of the ImageNet benchmark is available. The source code is available at https://github.com/google/lecam-gan.

Subfields: Computer Vision and Pattern Recognition, Generative Models

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Generative Models

Citations in the corpus

Make-A-Scene: Scene-Based Text-to-Image Generation with Human Priors (2022, background): “Generative Adversarial Networks (GANs) [17] facilitate the generation of high ﬁdelity images [29, 3, 30, 56] in multiple domains by simultaneously training a generator network G and a discriminator network D , where G is trained to fool D , while D is trained to judge if a given image is real or…”
StyleGAN-NADA (2021, background): “Others introduce new parameters in order to control channelwise statistics [28], leverage a miner network in order to steer GAN sampling towards suitable regions of the latent space [45], add novel regularization terms to the loss function [22, 42] or mix contrastive learning ideas with patchlevel d”
Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation (2023, methodology): “Following Yu et al. (2023a), we use LeCAM regularization (Tseng et al., 2021) for improved stability.”
Text as Neural Operator:Image Manipulation by Text Instruction (2020, background): “Built on the basis of GANs, the conditional GAN aims to synthesize the image according to some input context.”