Fostering Diversity in Spatial Evolutionary Generative Adversarial Networks
This addresses mode collapse issues in GANs for generative modeling, but it is incremental as it builds on existing CoE-GAN methods.
The paper tackled training pathologies like instability and mode collapse in GANs by introducing Mustangs, a spatially distributed CoE-GAN that uses different loss functions to foster diversity, resulting in statistically more accurate generators on MNIST and CelebA datasets.
Generative adversary networks (GANs) suffer from training pathologies such as instability and mode collapse, which mainly arise from a lack of diversity in their adversarial interactions. Co-evolutionary GAN (CoE-GAN) training algorithms have shown to be resilient to these pathologies. This article introduces Mustangs, a spatially distributed CoE-GAN, which fosters diversity by using different loss functions during the training. Experimental analysis on MNIST and CelebA demonstrated that Mustangs trains statistically more accurate generators.