P2D: Plug and Play Discriminator for Accelerating GAN Frameworks

Min Jin Chong, Krishna Kumar Singh, Yijun Li, Jingwan Lu, David Forsyth; Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2024, pp. 5422-5431

Most image classification tasks benefit from using pretrained feature stacks. In contrast, the discriminator for adversarial losses is trained at the same time as the model because using a pretrained feature stack yields a very poor model. Recent work has shown that an implicit regularization scheme allows using pretrained feature stacks to construct a discriminator, which improves both speed of training and quality of results. However, we observe that changes in hyperparameters can result in substantial changes in generator behavior. We show that using a modified version of the R1 regularization scheme that regularizes in the feature space instead of the image space results in a plug-and-play discriminator -- P2D. Our scheme results in a method that is highly stable across changes in architecture and framework; that significantly speeds up training; and that produces models that reliably beat SOTA in quality. The huge reduction in training resources required means that P2D could make training powerful generative models over specific datasets accessible to most researchers.