HingeRLC-GAN: Combating Mode Collapse with Hinge Loss and RLC Regularization
This addresses mode collapse for GAN users by offering an incremental improvement in training stability and diversity.
The paper tackled mode collapse in GANs by proposing HingeRLC-GAN, which combines RLC regularization and hinge loss, achieving a FID score of 18 and KID score of 0.001 to outperform existing methods.
Recent advances in Generative Adversarial Networks (GANs) have demonstrated their capability for producing high-quality images. However, a significant challenge remains mode collapse, which occurs when the generator produces a limited number of data patterns that do not reflect the diversity of the training dataset. This study addresses this issue by proposing a number of architectural changes aimed at increasing the diversity and stability of GAN models. We start by improving the loss function with Wasserstein loss and Gradient Penalty to better capture the full range of data variations. We also investigate various network architectures and conclude that ResNet significantly contributes to increased diversity. Building on these findings, we introduce HingeRLC-GAN, a novel approach that combines RLC Regularization and the Hinge loss function. With a FID Score of 18 and a KID Score of 0.001, our approach outperforms existing methods by effectively balancing training stability and increased diversity.