An Adaptive Control Algorithm for Stable Training of Generative Adversarial Networks

Generative adversarial networks (GANs) have shown significant progress in generating high-quality visual samples, however they are still well known both for being unstable to train and for the problem of mode collapse, particularly when trained on data collections containing a diverse set of visual objects. In this paper, we propose an Adaptive-step Generative Adversarial Network (-GAN), which is designed to mitigate the impact of instability and saturation in the original by dynamically adjusting the ratio of the training steps of both the generator and discriminator. To accomplish this, we track and analyze stable training curves of relatively narrow datasets and use them as the target fitting lines when training more diverse data collections. Furthermore, we conduct experiments on the proposed procedure using several optimization techniques (e.g., supervised guiding from previous stable learning curves with and without momentum) and compare their performance with that of state-of-the-art models on the task of image synthesis from datasets consisting of diverse images. Empirical results demonstrate that Ak-GAN works well in practice and exhibits more stable behavior than regular GANs during training. A quantitative evaluation has been conducted on the Inception Score (IS) and the relative inverse Inception Score (RIS); compared with regular GANs, the former has been improved by 61% and 83%, and the latter by 21% and 60%, on the CelebA and the Anime datasets, respectively.