生成对抗网络的惩罚梯度归一化
Penalty Gradient Normalization for Generative Adversarial Networks
AI总结：
本文提出惩罚梯度归一化（PGN）方法，通过对判别器施加梯度范数约束，增强其容量，稳定GAN训练，并在三个数据集上优于现有方法，提升FID和IS指标。
摘要：
本文提出了一种新颖的归一化方法，称为惩罚梯度归一化（PGN），以解决由尖锐梯度空间引起的生成对抗网络（GANs）训练不稳定的问题。与现有工作如梯度惩罚和谱归一化不同，所提出的PGN仅对判别器函数施加惩罚梯度范数约束，这增加了判别器的容量。此外，所提出的惩罚梯度归一化可以以少量修改应用于不同的GAN架构。在三个数据集上的大量实验表明，使用惩罚梯度归一化训练的GAN在Frechet Inception Distance和Inception Score方面均优于现有方法。
英文摘要：
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 existing work such as gradient penalty and spectral normalization, the proposed PGN only imposes a penalty gradient norm constraint on the discriminator function, which increases the capacity of the discriminator. Moreover, the proposed penalty gradient normalization can be applied to different GAN architectures with little modification. Extensive experiments on three datasets show that GANs trained with penalty gradient normalization outperform existing methods in terms of both Frechet Inception and Distance and Inception Score.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
