Generative adversarial networks (GANs) are 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. This study introduces an adaptive hyper-parameter learning procedure for GANs as an alternative to the existing static approach. The proposed procedure 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. Experimental results show that the proposed model improves the stability and generates more realistic images.
This work was supported in part by the MSIP (Ministry of Science and ICT) under ICT R&D program (2017-0-01672) supervised by the IITP (Institute for Information & communications Technology Promotion), in part by the National Natural Science Foundation of China (NSFC) under Grant 61806142.