GAN Resources

Written on December 4, 2017

Re-post of the resources list that was published to Piazza following the video lecture on Generative Adversarial Networks that Andy Brown and I created for Brian Hutchinson’s Deep Learning course at Western Washington University.

Key Papers


Generative Adversarial Networks (2014)
Original paper.

Improved Techniques for Training GANs (2016)
Follow up paper from original authors.

Wasserstein Generative Adversarial Networks (2017)
A popular new method for training GANs that proposes to solve the mode collapse problem.

Towards Principled Methods for Training GANs (2017)
A good follow up to original authors’ 2016 paper.

Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks (2016)
The paper that introduces the “reverse convolution” neural nets for generating images.

Other Stuff


Ian Goodfellow’s NIPS workshop [pdf, long video]
Probably the most referenced “starting point” for GANs outside of the actual paper.

Yann LeCun’s NIPS workshop
More recent, also covers energy based variant.

Medium blogs
UIUC Slides
Which I found helpful.

Stopping GAN Violence: Generative Unadversarial Networks
SIGBOVIK 17 (satirical CS publication) paper.

Cool Results & Applications


Image-to-Image Translation with Conditional Adversarial Nets (2017) [pdf, blog, github]
Phillip Isola, Jun-Yan Zhu, Tinghui Zhou, Alexei A. Efros
Drawing

StackGAN: Text to Image Synthesis with Stacked Generative Adversarial Networks (2016) [pdf, github]
Han Zhang, Tao Xu, Hongsheng Li, Shaoting Zhang, Xiaogang Wang, Xiaolei Huang, Dimitris Metaxas
Drawing

High-Resolution Image Synthesis with Conditional GANs (2017) [pdf, blog, github]
Ting-Chun Wang, Ming-Yu Liu, Jun-Yan Zhu, Andrew Tao, Jan Kautz, Bryan Catanzaro
Drawing Drawing

CycleGAN (2017) [pdf, blog, github]
Jun-Yan Zhu, Taesung Park, Phillip Isola, Alexei A. Efros Drawing

Progressive Growing of GANs for Improved Quality, Stability, and Variation (2017) [pdf, github, video]
Tero Karras, Timo Aila, Samuli Laine, Jaakko Lehtinen
Drawing
Picture: Two imaginary celebrities that were dreamed up by a random number generator.

StarGAN: Generative Adversarial Networks for Image-to-Image Translation (2017) [pdf, github]
Yunjey Choi, Minje Choi, Munyoung Kim, Jung-Woo Ha, Sunghun Kim, Jaegul Choo
Drawing

More examples:

Cryptography
Video Generation
Art
Coloring Anime Sketches
Image to Video