Improved Consistency Regularization for GANs
Recent work has increased the performance of Generative Adversarial Networks (GANs) by enforcing a consistency cost on the discriminator. We improve on this technique in several ways. We first show that consistency regularization can introduce artifacts into the GAN samples and explain how to fix this issue. We then propose several modifications to the consistency regularization procedure designed to improve its performance. We carry out extensive experiments quantifying the benefit of our improvements. For unconditional image synthesis on CIFAR-10 and CelebA, our modifications yield the best known FID scores on various GAN architectures. For conditional image synthesis on CIFAR-10, we improve the state-of-the-art FID score from 11.48 to 9.21. Finally, on ImageNet-2012, we apply our technique to the original BigGAN model and improve the FID from 6.66 to 5.38, which is the best score at that model size.
Code (0)
등록된 구현이 없습니다.
Tasks
Image GenerationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Orthogonal Wasserstein GANs
Wasserstein-GANs have been introduced to address the deficiencies of generative adversarial networks (GANs) regarding the problems of vanishing gradients and mode collapse during the training, leading to improved converg…
Augmented Cyclic Consistency Regularization for Unpaired Image-to-Image Translation
Unpaired image-to-image (I2I) translation has received considerable attention in pattern recognition and computer vision because of recent advancements in generative adversarial networks (GANs). However, due to the lack …
Data AugmentationImage-to-Image TranslationTranslationImage Augmentations for GAN Training
Data augmentations have been widely studied to improve the accuracy and robustness of classifiers. However, the potential of image augmentation in improving GAN models for image synthesis has not been thoroughly investig…
Image AugmentationImage GenerationAn Improved Composite Functional Gradient Learning by Wasserstein Regularization for Generative adversarial networks
Generative adversarial networks (GANs) are usually trained by a minimax game which is notoriously and empirically known to be unstable. Recently, a totally new methodology called Composite Functional Gradient Learning (…
Image GenerationregressionPairing Regularization for Mitigating Many-to-One Collapse in GANs
Mode collapse remains a fundamental challenge in training generative adversarial networks (GANs). While existing works have primarily focused on inter-mode collapse, such as mode dropping, intra-mode collapse-where many …