目录
优点:
缺点:
Generative Adversarial Nets, Goodfellow et al, NIPS 2014
https://ishmaelbelghazi.github.io/ALI
DCGAN: Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks, Radford et al, ICLR 2015
反卷积(实际是卷积把步长调成>=2)
模型崩溃——minibatch GAN (Salimans et al, NIPS 2016)
Generative Adversarial Text to Image Synthesis, Reed et al, ICML 2016 原来GAN输入只是噪音,现在多一些其他维度的描述(例如,文本)
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network, Ledig et al, arxiv 2016
针对小数据集,传统方法+nn比直接上nn其实差不多(deepface)