A U-Net Based Discriminator for Generative Adversarial Networks
Among the major remaining challenges for generative adversarial networks (GANs) is the capacity to synthesize globally and locally coherent images with object shapes and textures indistinguishable from real images. To target this issue we propose an alternative U-Net based discriminator architecture, borrowing the insights from the segmentation literature. The proposed U-Net based architecture allows to provide detailed per-pixel feedback to the generator while maintaining the global coherence of synthesized images, by providing the global image feedback as well. Empowered by the per-pixel response of the discriminator, we further propose a per-pixel consistency regularization technique based on the CutMix data augmentation, encouraging the U-Net discriminator to focus more on semantic and structural changes between real and fake images. This improves the U-Net discriminator training, further enhancing the quality of generated samples. The novel discriminator improves over the state of the art in terms of the standard distribution and image quality metrics, enabling the generator to synthesize images with varying structure, appearance and levels of detail, maintaining global and local realism. Compared to the BigGAN baseline, we achieve an average improvement of 2.7 FID points across FFHQ, CelebA, and the newly introduced COCO-Animals dataset. The code is available at https://github.com/boschresearch/unetgan.
Code (3)
Tasks
Conditional Image GenerationData AugmentationImage GenerationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
O-GAN: Extremely Concise Approach for Auto-Encoding Generative Adversarial Networks
In this paper, we propose Orthogonal Generative Adversarial Networks (O-GANs). We decompose the network of discriminator orthogonally and add an extra loss into the objective of common GANs, which can enforce discriminat…
Generative Adversarial NetworkInvestigating Under and Overfitting in Wasserstein Generative Adversarial Networks
We investigate under and overfitting in Generative Adversarial Networks (GANs), using discriminators unseen by the generator to measure generalization. We find that the model capacity of the discriminator has a significa…
Generalized Dual Discriminator GANs
Dual discriminator generative adversarial networks (D2 GANs) were introduced to mitigate the problem of mode collapse in generative adversarial networks. In D2 GANs, two discriminators are employed alongside a generator:…
CapsuleGAN: Generative Adversarial Capsule Network
We present Generative Adversarial Capsule Network (CapsuleGAN), a framework that uses capsule networks (CapsNets) instead of the standard convolutional neural networks (CNNs) as discriminators within the generative adver…
General ClassificationGenerative Adversarial Networkimage-classificationImage Classification+1EGANS: Evolutionary Generative Adversarial Network Search for Zero-Shot Learning
Zero-shot learning (ZSL) aims to recognize the novel classes which cannot be collected for training a prediction model. Accordingly, generative models (e.g., generative adversarial network (GAN)) are typically used to sy…
Generative Adversarial NetworkNeural Architecture SearchZero-Shot Learning