paper-with-me

Papers

Generator Knows What Discriminator Should Learn in Unconditional GANs

2022-07-27 · Gayoung Lee, Hyunsu Kim, Junho Kim, Seonghyeon Kim, Jung-Woo Ha, Yunjey Choi

Recent methods for conditional image generation benefit from dense supervision such as segmentation label maps to achieve high-fidelity. However, it is rarely explored to employ dense supervision for unconditional image generation. Here we explore the efficacy of dense supervision in unconditional generation and find generator feature maps can be an alternative of cost-expensive semantic label maps. From our empirical evidences, we propose a new generator-guided discriminator regularization(GGDR) in which the generator feature maps supervise the discriminator to have rich semantic representations in unconditional generation. In specific, we employ an U-Net architecture for discriminator, which is trained to predict the generator feature maps given fake images as inputs. Extensive experiments on mulitple datasets show that our GGDR consistently improves the performance of baseline methods in terms of quantitative and qualitative aspects. Code is available at https://github.com/naver-ai/GGDR

📄 PDF Abstract BibTeX arXiv:2207.13320

Code (1)

naver-ai/ggdr 공식 구현 pytorch

Tasks

Conditional Image GenerationImage GenerationUnconditional Image Generation

Methods 이 논문이 사용한 방법론

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…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
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…
U-Net 설명 없음

Similar Papers 제목 키워드 기반

The Benefits of Pairwise Discriminators for Adversarial Training

2020-02-20 · Shangyuan Tong, Timur Garipov, Tommi Jaakkola

Adversarial training methods typically align distributions by solving two-player games. However, in most current formulations, even if the generator aligns perfectly with data, a sub-optimal discriminator can still drive…

Learning to Sample Replacements for ELECTRA Pre-Training

2021-06-25 · Findings (ACL) 2021 8 · Yaru Hao, Li Dong, Hangbo Bao, Ke Xu 외

ELECTRA pretrains a discriminator to detect replaced tokens, where the replacements are sampled from a generator trained with masked language modeling. Despite the compelling performance, ELECTRA suffers from the followi…

Language ModelingLanguage ModellingMasked Language Modeling

TopoAL: An Adversarial Learning Approach for Topology-Aware Road Segmentation

2020-07-17 · ECCV 2020 8 · Subeesh Vasu, Mateusz Kozinski, Leonardo Citraro, Pascal Fua

Most state-of-the-art approaches to road extraction from aerial images rely on a CNN trained to label road pixels as foreground and remainder of the image as background. The CNN is usually trained by minimizing pixel-wis…

Road Segmentation

StyleGAN-V: A Continuous Video Generator with the Price, Image Quality and Perks of StyleGAN2

2021-12-29 · CVPR 2022 1 · Ivan Skorokhodov, Sergey Tulyakov, Mohamed Elhoseiny

Videos show continuous events, yet most $-$ if not all $-$ video synthesis frameworks treat them discretely in time. In this work, we think of videos of what they should be $-$ time-continuous signals, and extend the par…

Video Generation

Lifelong Twin Generative Adversarial Networks

2021-07-09 · Fei Ye, Adrian G. Bors

In this paper, we propose a new continuously learning generative model, called the Lifelong Twin Generative Adversarial Networks (LT-GANs). LT-GANs learns a sequence of tasks from several databases and its architecture c…

Knowledge Distillation