CVNov 13, 2016

Least Squares Generative Adversarial Networks

arXiv:1611.04076v35034 citations
Originality Incremental advance
AI Analysis

This addresses stability and quality issues in GAN training for image generation, representing an incremental improvement over existing methods.

The paper tackled the vanishing gradients problem in regular GANs by proposing Least Squares GANs (LSGANs) with a least squares loss function, resulting in higher quality image generation and more stable learning, as shown by better experimental results on five scene datasets.

Unsupervised learning with generative adversarial networks (GANs) has proven hugely successful. Regular GANs hypothesize the discriminator as a classifier with the sigmoid cross entropy loss function. However, we found that this loss function may lead to the vanishing gradients problem during the learning process. To overcome such a problem, we propose in this paper the Least Squares Generative Adversarial Networks (LSGANs) which adopt the least squares loss function for the discriminator. We show that minimizing the objective function of LSGAN yields minimizing the Pearson $χ^2$ divergence. There are two benefits of LSGANs over regular GANs. First, LSGANs are able to generate higher quality images than regular GANs. Second, LSGANs perform more stable during the learning process. We evaluate LSGANs on five scene datasets and the experimental results show that the images generated by LSGANs are of better quality than the ones generated by regular GANs. We also conduct two comparison experiments between LSGANs and regular GANs to illustrate the stability of LSGANs.

Code Implementations24 repos

Data from Papers with Code (CC-BY-SA-4.0)

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes