A U-Net Based Discriminator for Generative Adversarial Networks

2020-06-01 · CVPR 2020 6 · Edgar Schonfeld, Bernt Schiele, Anna Khoreva

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 proposed COCO-Animals dataset.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Data Augmentation

Methods 이 논문이 사용한 방법론

U-Net GAN In contrast to typical GANs, a U-Net GAN uses a segmentation network as the discriminator. This segmentation network predicts two classes: real and fake. In doing so, the…

Concatenated Skip Connection A Concatenated Skip Connection is a type of skip connection that seeks to reuse features by concatenating them to new layers, allowing more information to be retained from…

Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Six Ways To Communicate To Someone At Expedia Via Phone And Email's. To communicate or get human at Expedia, the quickest option is typically to call their customer service at ＋１－８８８－８２９－０８８１　ｏｒ　＋１（８０５）　３３０　（４０５６）. You can also use the live chat…

U-Net 설명 없음

((Reservation@Faqs))How do I cancel a reservation on Expedia? How do I cancel a reservation on Expedia? +1^888^829^0881° oR +1^888^829^0881 – Need to cancel your Expedia reservation quickly and without hassle? This step-by-step guide…

Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

O-GAN: Extremely Concise Approach for Auto-Encoding Generative Adversarial Networks

2019-03-05 · Jianlin Su

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 Network

Investigating Under and Overfitting in Wasserstein Generative Adversarial Networks

2019-10-30 · Ben Adlam, Charles Weill, Amol Kapoor

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

2025-07-23 · Penukonda Naga Chandana, Tejas Srivastava, Gowtham R. Kurri, V. Lalitha arxiv

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

2018-02-17 · Ayush Jaiswal, Wael Abd-Almageed, Yue Wu, Premkumar Natarajan

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 Classification Generative Adversarial Network image-classification Image Classification+1

EGANS: Evolutionary Generative Adversarial Network Search for Zero-Shot Learning

2023-08-19 · Shiming Chen, Shihuang Chen, Wenjin Hou, Weiping Ding 외

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 Network Neural Architecture Search Zero-Shot Learning