Improved Training of Wasserstein GANs
Citations
5,354 citations
4,584 citations
2,640 citations
2,411 citations
Cites background from "Improved Training of Wasserstein GA..."
...Skip connections [29, 19], residual networks [15, 14, 26], and hierarchical methods [6, 41, 42] have proven highly successful also in the context of generative methods....
[...]
2,298 citations
References
111,197 citations
38,211 citations
"Improved Training of Wasserstein GA..." refers background in this paper
...In practice, [9] advocates that the generator be instead trained to maximize E x̃⇠P...
[...]
...[9], but doing so often leads to vanishing gradients as the discriminator saturates....
[...]
...† 1 Introduction Generative Adversarial Networks (GANs) [9] are a powerful class of generative models that cast generative modeling as a game between two networks: a generator network produces synthetic data given some noise source and a discriminator network discriminates between the generator’s output and true data....
[...]
23,486 citations
15,005 citations
7,930 citations
"Improved Training of Wasserstein GA..." refers methods in this paper
...Other attempts at language modeling with GANs [31, 14, 29, 5, 15, 10] typically use discrete models and gradient estimators [27, 12, 16]....
[...]