Adversarial Generator-Encoder Networks

By Dmitry Ulyanov, Andrea Vedaldi, Victor S. Lempitsky. 2017

39 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Generative Models

Citations in the corpus

Progressive Growing of GANs for Improved Quality, Stability, and Variation (2017, methodology): “Hybrid methods combine various strengths of the three, but so far lag behind GANs in image quality (Makhzani & Frey, 2017; Ulyanov et al., 2017; Dumoulin et al., 2016).”
Good Semi-supervised Learning That Requires a Bad GAN (2017, neutral): “The same phenomenon was also observed in [21], where the model generated better images but failed to improve the performance on semi-supervised learning.”
MMD GAN: Towards Deeper Understanding of Moment Matching Network (2017, critical): “[27] is similar to MMD GAN but it considers KL-divergence without showing continuity and weak⇤ topology guarantee as we prove in Section 2.”
Variational Approaches for Auto-Encoding Generative Adversarial Networks (2017, methodology): “We explore the same approximation (also used by AGE) in Section D in the Appendix.”
Mutual Information Neural Estimation (2018, background): “Reconstructions are one desirable property of a model that does both inference and generation, but in practice ALI can lack ﬁdelity (i.e., reconstructs less faithfully than desired, see Li et al., 2017; Ulyanov et al., 2017; Belghazi et al., 2018).”
Generative adversarial interpolative autoencoding: adversarial training on latent space interpolations encourage convex latent distributions (2018, methodology): “A number of other adversarial network architectures (e.g. Larsen et al. 2015; Mescheder et al. 2017; Berthelot et al. 2017; Dumoulin et al. 2016; Ulyanov et al. 2017; Makhzani 2018) have been designed with a similar motivation in recent years.”
Hierarchical Adversarially Learned Inference (2018, background): “Ulyanov et al. (2017) show that an improvement in reconstructions is achievable when additional terms which explicitly minimize reconstruction error in the data space are added to the training objective.”
Auto-Embedding Generative Adversarial Networks For High Resolution Image Synthesis (2019, methodology): “To achieve this, one can compare the distribution divergences of the real and the generated data in a low-dimensional data space, such as StackGAN [56], StackGAN-v2 [39], AGE [42] and AttnGAN [33].”
Pioneer Networks: Progressively Growing Generative Autoencoder (2018, methodology): “After the progressive growth phase of the training, we switched to λX = 15 d to emphasize sample reconstruction [26].”
How Generative Adversarial Networks and Their Variants Work (2017, background): “(Z) Encoder X Generator Latent space Z E(X) Discriminator Z,G(Z) E(X),Z (a)ALI,BiGAN Data space G(E(X)) G(Z) X E(X) Encoder Generator Latent space Z R E(G(Z)) R (b)AGE Figure8: ALI[25],BiGAN[24]andAGE[108] Somemethodsadoptpolicygradientalgorithm[102]inReinforcementLearning(RL)whoseobject is to maxim”
How Generative Adversarial Networks and Its Variants Work : An Overview of GAN (2017, background): “[35]: Standard GAN, [73]: LSGAN, [138]: EBGAN, [6]: WGAN, [97]: Improved WGAN, [80]: McGAN, [10]: CramerGAN, [65]: MMDGAN, [79]: FisherGAN, [76]: Unrolled GAN, [14]: MRGAN, [59]: DRAGAN, [77]: Conditional GAN, [16]: InfoGAN, [106]: ss-InfoGAN, [27]: ALI, [25]: BiGAN, [116]: AGE, [58]: ARAE, [61]: VA”
Optimizing the Latent Space of Generative Networks (2017, background): “For instance, Zhao et al. [2016] replace the discrimi-nator of a GAN by an AE, and Ulyanov et al. [2017] replace the decoder of an AE by a generator of a GAN.”