Improved Training with Curriculum GANs
This addresses the challenge of unstable GAN training for researchers and practitioners in machine learning, though it appears incremental as it builds on existing curriculum learning concepts.
The paper tackles the problem of training Generative Adversarial Networks (GANs) by introducing Curriculum GANs, a curriculum learning strategy that progressively increases discriminator strength, resulting in state-of-the-art image generation performance.
In this paper we introduce Curriculum GANs, a curriculum learning strategy for training Generative Adversarial Networks that increases the strength of the discriminator over the course of training, thereby making the learning task progressively more difficult for the generator. We demonstrate that this strategy is key to obtaining state-of-the-art results in image generation. We also show evidence that this strategy may be broadly applicable to improving GAN training in other data modalities.