Progressive Augmentation of GANs
This addresses the stability problem in GAN training for researchers and practitioners, offering an incremental improvement over existing methods.
The paper tackles the fragility of training Generative Adversarial Networks (GANs) by introducing a progressive augmentation technique (PA-GAN) that gradually increases discriminator task difficulty, resulting in an average ~3 point improvement in FID score for image synthesis across benchmarks.
Training of Generative Adversarial Networks (GANs) is notoriously fragile, requiring to maintain a careful balance between the generator and the discriminator in order to perform well. To mitigate this issue we introduce a new regularization technique - progressive augmentation of GANs (PA-GAN). The key idea is to gradually increase the task difficulty of the discriminator by progressively augmenting its input or feature space, thus enabling continuous learning of the generator. We show that the proposed progressive augmentation preserves the original GAN objective, does not compromise the discriminator's optimality and encourages a healthy competition between the generator and discriminator, leading to the better-performing generator. We experimentally demonstrate the effectiveness of PA-GAN across different architectures and on multiple benchmarks for the image synthesis task, on average achieving ~3 point improvement of the FID score.