paper-with-me

Papers

Gradient Normalization for Generative Adversarial Networks

2021-09-06 · ICCV 2021 10 · Yi-Lun Wu, Hong-Han Shuai, Zhi-Rui Tam, Hong-Yu Chiu

In this paper, we propose a novel normalization method called gradient normalization (GN) to tackle the training instability of Generative Adversarial Networks (GANs) caused by the sharp gradient space. Unlike existing work such as gradient penalty and spectral normalization, the proposed GN only imposes a hard 1-Lipschitz constraint on the discriminator function, which increases the capacity of the discriminator. Moreover, the proposed gradient normalization can be applied to different GAN architectures with little modification. Extensive experiments on four datasets show that GANs trained with gradient normalization outperform existing methods in terms of both Frechet Inception Distance and Inception Score.

📄 PDF Abstract BibTeX arXiv:2109.02235

Code (1)

basiclab/gngan-pytorch 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

Gradient Normalization 설명 없음

Similar Papers 제목 키워드 기반

Penalty Gradient Normalization for Generative Adversarial Networks

2023-06-23 · Tian Xia

In this paper, we propose a novel normalization method called penalty gradient normalization (PGN) to tackle the training instability of Generative Adversarial Networks (GANs) caused by the sharp gradient space. Unlike e…

GraN-GAN: Piecewise Gradient Normalization for Generative Adversarial Networks

2021-11-04 · Vineeth S. Bhaskara, Tristan Aumentado-Armstrong, Allan Jepson, Alex Levinshtein

Modern generative adversarial networks (GANs) predominantly use piecewise linear activation functions in discriminators (or critics), including ReLU and LeakyReLU. Such models learn piecewise linear mappings, where each …

Image Generation

ABCAS: Adaptive Bound Control of spectral norm as Automatic Stabilizer

2022-11-12 · Shota Hirose, Shiori Maki, Naoki Wada, Heming Sun 외

Spectral Normalization is one of the best methods for stabilizing the training of Generative Adversarial Network. Spectral Normalization limits the gradient of discriminator between the distribution between real data and…

Generative Adversarial Network

Towards Efficient and Unbiased Implementation of Lipschitz Continuity in GANs

2019-04-02 · Zhiming Zhou, Jian Shen, Yuxuan Song, Wei-Nan Zhang 외

Lipschitz continuity recently becomes popular in generative adversarial networks (GANs). It was observed that the Lipschitz regularized discriminator leads to improved training stability and sample quality. The mainstrea…

Adversarial Lipschitz Regularization

2019-07-12 · ICLR 2020 1 · Dávid Terjék

Generative adversarial networks (GANs) are one of the most popular approaches when it comes to training generative models, among which variants of Wasserstein GANs are considered superior to the standard GAN formulation …

Image Generation