Progressive Augmentation of GANs
Dan Zhang · Anna Khoreva

Wed Dec 11th 10:45 AM -- 12:45 PM @ East Exhibition Hall B + C #118

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.

Author Information

Dan Zhang (Bosch Center for Artificial Intelligence)
Anna Khoreva (Bosch Center for Artificial Intelligence)

More from the Same Authors