Generative Adversarial Networks
Generative Adversarial Network, GAN in a brief, is one of the breakthrough of learning framework which was born in 2014 with Good fellow and earth. Al research at NeuroIPS(NIPS) conference.
On this page, I want to publish some useful tips for guiding you about Generative Adversarial Networks. I paraphrase them in three sections such as definitions, implementation experience and applications.
Don't hesitate to contact me if you have any notes about improving these guidelines and also counseling about academical/industrial projects with related Adversarial learning topic.
khalooei [at] aut.ac.ir
Level 0: Definition of GANs
Some of the useful references about definitions of Generative Adversarial Network listed as below:
| Level | Title | Co-authors | Publication | Links |
|---|---|---|---|---|
| Beginner | GAN : Generative Adversarial Nets | Goodfellow & et al. | NeurIPS (NIPS) 2014 | Download Code |
| Beginner | GAN : Generative Adversarial Nets (Tutorial) | Goodfellow & et al. | NeurIPS (NIPS) 2016 Tutorial | Download |
| Beginner | CGAN : Conditional Generative Adversarial Nets | Mirza & et al. | -- 2014 | Download Abstract Code |
| Beginner | InfoGAN : Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets | Chen & et al. | NeuroIPS (NIPS) 2016 | Download Code |
| Intermediate | AAE : Adversarial Autoencoders | Makhzani & et al. | ICLR 2016 | Download Code |
| BOOK | Advanced Deep Learning with Keras | Atienza | published by Packt | Book Github |
Level 1: Improvements of GANs training
Some of the useful references about stabilizing the training procedure of Generative Adversarial Network listed as below:
| Level | Title | Co-authors | Publication | Links |
|---|---|---|---|---|
| Beginner | LSGAN : Least Squares Generative Adversarial Networks | Mao & et al. | ICCV 2017 | Download |
| Advanced | Improved Techniques for Training GANs | Salimans & et al. | NeurIPS (NIPS) 2016 | Download |
| Advanced | WGAN : Wasserstein GAN | Arjovsky & et al. | ICML 2017 | Download Code |
| Advanced | Certifying Some Distributional Robustness with Principled Adversarial Training | Sinha & et al. | ICML 2018 | Download Reviews Code |
Level 3: Implementation skill
In this section, I gathered some influences paper which was useful for GAN implementation experience:
| Title | Co-authors | Publication | Links |
|---|---|---|---|
| Keras Implementation of GANs | Linder-Norén | Github | Codes |
| GAN implementation hacks | Salimans paper & Chintala | World research | Paper Hack Proposals |
| DCGAN : Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks | Radford & et al. | ICLR 2016 | Download Code |
| IcGAN: Invertible Conditional GANs for image editing | Arjovsky & et al. | NIPS 2016 | Download Code |
| AutoGAN: AutoML + GAN = AutoGAN :: Neural Architecture Search for Generative Adversarial Networks | Gong & et al. | ICCV 2019 | Download Code |
Level 4: GANs Applications
In this section, I gathered some useful researches which use GAN in their infrastructure:
| Title | Co-authors | Publication | Links |
|---|---|---|---|
| CycleGAN: Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks | Zhu & Park & et al. | ICCV 2017 | Download Code |
| IcGAN: Invertible Conditional GANs for image editing | Arjovsky & et al. | NIPS 2016 | Download Code |
| Generative Adversarial Text to Image Synthesis | Reed & et al. | ICML 2016 | Download Code |
| StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks | Zhang & et al. | ICCV 2017 | Download Code |
| Conditional Generative Adversarial Networks for Speech Enhancement and Noise-Robust Speaker Verification | Michelsanti & Tan | Interspeech 2017 | Download |
| Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network | Ledig & et al. | CVPR 2017 | Download Code |
| SalGAN: Visual Saliency Prediction with Generative Adversarial Networks | Pan & et al. | CVPR 2017 | Download Code |
| SAGAN: Self-Attention Generative Adversarial Networks | Zhang & et al. | NIPS 2018 | Download Code |
| Speaker Adaptation for High Fidelity WaveNet Vocoder with GAN | Tian & et al. | arXiv Nov 2018 | Download |
| MTGAN: Speaker Verification through Multitasking Triplet Generative Adversarial Networks | Ding & et al. | arXiv Mar 2018 | Download |
| Adversarial Learning and Augmentation for Speaker Recognition | Zhang & et al. | Speaker Odyssey 2018 / ISCA 2018 | Download |
| Investigating Generative Adversarial Networks based Speech Dereverberation for Robust Speech Recognition | Wang & et al. | Interspeech 2018 | Download |
| On Enhancing Speech Emotion Recognition using Generative Adversarial Networks | Sahu & et al. | Interspeech 2018 | Download |
| Robust Speech Recognition Using Generative Adversarial Networks | Sriram & et al. | ICASSP 2018 | Download Code |
| Adversarially Learned One-Class Classifier for Novelty Detection | Sabokrou & khalooei & et al. | CVPR 2018 | Download Code |
| Generalizing to Unseen Domains via Adversarial Data Augmentation | Volpi & et al. | NeurIPS (NIPS) 2018 | Download |
| Generative Adversarial Networks for Unpaired Voice Transformation on Impaired Speech | Chen & lee & et al. | Submitted on ICASSP 2019 | Download Code |
| Generative Adversarial Speaker Embedding Networks for Domain Robust End-to-End Speaker Verification | Bhattacharya & et al. | Submitted on ICASSP 2019 | Download |