Three Approaches to Generative Models

• [Generative Adversarial Networks (GANs)]
  • Different Versions of GANs
  • GANs Comparision
  • GANs Survey for Vision
  • Variants of GAN Architecture
  • GAN Value Functions
  • References
  • Paper Review
• [Variational Autoencoders (VAEs)]
  • Autoencoders
• [Autoregressive models]
  • [EX: PixelRNN]

Back to top

---

Different Versions of GANs

Back to top

(I have listed below GANs based on their timelines, since from GANs inception(Jun 2014))

• [DCGANs]
• [cGANs]
• [InfoGANs]
• [Wasserstein GANs]
• [LAPGAN]
• [GRAN ]
• [BiGANs]
• [f-GAN]
• [CoGAN]
• [EBGAN]
• [iGAN]
• [SeqGAN]
• [RenderGAN]
• [VGAN]
• [LSGANs]
• [IcGAN]
• [TGAN]
• [SAD-GAN]
• [C-RNN-GAN]
• [AANs]
• [StackGAN]
• [SGAN]
• [SalGAN]
• [AdaGAN]
• [GLS-GAN]
• [ArtGAN]
• [BS-GAN]
• [AM-GAN]
• [Triple-GAN]
• [DiscoGAN]
• [SEGAN]
• [CVAE-GAN]
• [SeGAN]
• [CycleGAN]
• [BEGAN]
• [MidiNet]
• [Semi-Latent GAN]
• [DualGAN]
• [A-Fast-RCNN]
• [MAGAN]
• [Gang of GANs]
• [Softmax GAN]
• [Show, Adapt and Tell]
• [Geometric GAN]
• [GeneGAN]
• [Flow-GAN]
• [SegAN]
• [DeLiGAN]
• [StackGAN]
• [Flow-GAN]
• [GraphGAN]
• [MuseGAN]
• [OptionGAN]
• [RAN4IQA]
• [Show, Reward and Tell]

More GANs --> The GAN Zoo

---

References

Back to top

• Generative Adversarial Networks: An Overview [arXiv]
• NIPS 2016 Tutorial: Generative Adversarial Networks
• Survey on Generative Adversarial Networks
• Comparative Study on Generative Adversarial Networks
• GAN Lab: Understanding Complex Deep Generative Models using Interactive Visual Experimentation
• A Survey of Image Synthesis and Editing with Generative Adversarial Networks
• OpenAI: Generative Models
• Generative models
• Adversarial Examples: Attacks and Defenses for Deep Learning
• Generative Adversarial Nets for Information Retrieval: Fundamentals and Advances
• The GAN Landscape: Losses, Architectures, Regularization, and Normalization
• A Tale of Three Probabilistic Families: Discriminative, Descriptive and Generative Models
• QGAN: Quantized Generative Adversarial Networks

---

Paper Review

Back to top

• GAN-theory-and-ml
• GAN-ref-implementations
• GAN-applications
• GANs for vision

---

Maintainer

Gopala KR / @gopala-kr

---