Simple yet Effective Way for Improving the Performance of GAN
This addresses a key bottleneck in GAN training for image generation, offering a simple enhancement to existing methods, though it is incremental as it builds on standard frameworks.
The paper tackles the problem of discriminators in GANs focusing on non-robust features, which hinders generator guidance, by proposing a cascading rejection module that extracts diverse features to improve performance. The result is significant improvements in FID scores across multiple datasets like CIFAR-10 and CelebA, indicating better image quality and diversity.
In adversarial learning, discriminator often fails to guide the generator successfully since it distinguishes between real and generated images using silly or non-robust features. To alleviate this problem, this brief presents a simple but effective way that improves the performance of generative adversarial network (GAN) without imposing the training overhead or modifying the network architectures of existing methods. The proposed method employs a novel cascading rejection (CR) module for discriminator, which extracts multiple non-overlapped features in an iterative manner using the vector rejection operation. Since the extracted diverse features prevent the discriminator from concentrating on non-meaningful features, the discriminator can guide the generator effectively to produce the images that are more similar to the real images. In addition, since the proposed CR module requires only a few simple vector operations, it can be readily applied to existing frameworks with marginal training overheads. Quantitative evaluations on various datasets including CIFAR-10, CelebA, CelebA-HQ, LSUN, and tiny-ImageNet confirm that the proposed method significantly improves the performance of GAN and conditional GAN in terms of Frechet inception distance (FID) indicating the diversity and visual appearance of the generated images.