马尔科夫判别器PatchGAN

PatchGAN is a type of discriminator for generative adversarial networks which only penalizes structure at the scale of local image patches. The PatchGAN discriminator tries to classify if each N X N patch in an image is real or fake. This discriminator is run convolutionally across the image, averaging all responses to provide the ultimate output of D. Such a discriminator effectively models the image as a Markov random field, assuming independence between pixels separated by more than a patch diameter. It can be understood as a type of texture/style loss.（from）

PatchGAN一种仅在补丁范围内进行“惩罚”的生成对抗网络的一种鉴别器。PatchGAN鉴别器试图对图像中的每个N * N的patch进行分类是真实的还是虚假的。该鉴别器在图像上卷积运行，并对所有相应求平均以提提供鉴别器D的最终的输出。这样的鉴别器有效的地将图像建模为马尔科夫随机场，并假设相隔大于补丁直径的像素之间具有独立性，可以理解为一种纹理/样式损失。

参考：

1. https://www.pianshen.com/article/6107372960/
2. https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix/issues/39
3. https://www.dazhuanlan.com/2019/11/28/5ddf947945e4f/