Least Squares Generative Adversarial Networks: Theories and Applications

Description

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 this problem, we propose the Least Squares Generative Adversarial Networks (LSGANs), which adopt the least squares loss function for the discriminator. There are two benefits of LSGANs over regular GANs. First, LSGANs can generate higher-quality images than regular GANs. Second, LSGANs perform more stable during the learning process. We evaluate LSGANs on LSUN and CIFAR-10 datasets, and the experimental results show that the images generated by LSGANs are of better quality than those generated by regular GANs. In addition, the proposed LSGANs can be employed in domain-specific applications like data augmentation and image processing.

Period	30 May 2023
Event title	Data Science and AI Forum 2023
Event type	Forum
Location	Hong KongShow on map