weixin_44363205的博客

1、文献综述文章链接：链接文章题目：《Rob-GAN: Generator, Discriminator, and Adversarial Attacker》项目地址：源码2、文献导读本文提出一种新的框架Rob-GAN，该框架创新性的将对抗学习（Adversarial learning）和生成对抗网络（Generative Adversarial Networks）组成一个新的模型，其中...

1、文献综述文章链接：链接文章题目：《Self-Attention Generative Adversarial Networks》项目地址：1.TensorFlow版               \,\,\,\,\,\,\,\,\,\,\,\,\,\, 2.pytorch版2、文献导读本文提出了Self-Attention Generative Adversarial Networks...

1、文献综述文章链接：链接文章题目：《StoryGAN: A Sequential Conditional GAN for Story Visualization》项目地址：源码2、文献导读之前Text-to-Image的文章都是基于输入的一句话生成对应的图像，希望在生成图像足够逼真的前提下，同时尽可能的与输入语句所表达的语义信息保持一致性。而本文提出的StoryGAN可以实现根据一段连...

1、文献综述文章链接：链接文章题目：《Self-Supervised GANs via Auxiliary Rotation Loss》项目地址：源码

1、文献综述文章链接：链接文章题目：《MirrorGAN: Learning Text-to-image Generation by Redescription》代码尚未公布2、文献导读

•We propose a simple yet effective mode seeking regularization method to address the mode collapse problem in cGANs. This regularization scheme can be readily extended into existing frameworks with marginal training overheads and modifications.• We demons