Advanced GAN techniques
Chapter 1: GAN Foundations Revisited
The Generator-Discriminator Architecture
The Minimax Objective Function
Common Training Instabilities
Limitations of Vanilla GANs
Deep Convolutional GANs (DCGANs) Refresher
Chapter 2: Advanced GAN Architectures
Progressive Growing of GANs (ProGAN)
Style-Based Generator Architecture (StyleGAN)
StyleGAN2 Enhancements
Large Scale GAN Training (BigGAN)
Self-Attention Mechanisms in GANs
Unpaired Image-to-Image Translation (CycleGAN)
Implementing StyleGAN Components: Hands-on Practical
Chapter 3: GAN Training Dynamics and Stabilization
The Challenge of Non-Convergence
Mode Collapse: Causes and Consequences
Alternative Divergences: Wasserstein Distance
Weight Clipping in WGAN
Gradient Penalty (WGAN-GP)
Spectral Normalization
Two Time-Scale Update Rule (TTUR)
Relativistic GANs
Implementing WGAN-GP: Practice
Chapter 4: Conditional and Controllable Generation
Introduction to Conditional GANs (cGANs)
Architectures for cGANs
Information Maximizing GANs (InfoGAN)
StackGAN: Text-to-Image Synthesis
Controlling Attributes via Latent Space Manipulation
Disentanglement Metrics and Challenges
Building a Conditional GAN: Hands-on Practical
Chapter 5: Quantitative and Qualitative Evaluation of GANs
Challenges in Evaluating Generative Models
Qualitative Assessment: Visual Turing Tests
Inception Score (IS): Formulation and Limitations
Fréchet Inception Distance (FID): Formulation
Interpreting FID Scores
Precision and Recall for Distributions
Perceptual Path Length (PPL)
Calculating FID Score: Practice
Chapter 6: GANs Beyond Standard Image Generation
Challenges with Discrete Data: Text Generation
Reinforcement Learning Approaches (SeqGAN, RankGAN)
Continuous Approximations (Gumbel-Softmax)
Audio Synthesis with GANs (WaveGAN, SpecGAN)
Video Generation and Prediction
3D Data Generation (Point Clouds, Meshes)
Graph Generation with GANs
Chapter 7: Implementation, Optimization, and Tooling
Choosing Deep Learning Frameworks
Advanced Optimizers (AdamW, Lookahead)
Hyperparameter Tuning Strategies
Weight Initialization Techniques
Debugging Unstable GAN Training
Mixed Precision Training
Distributed Training Strategies for Large GANs
Profiling and Performance Optimization
Optimizing a GAN Implementation: Practice
Weight Clipping in WGAN
Was this section helpful?
- Wasserstein Generative Adversarial Networks, Martin Arjovsky, Soumith Chintala, and Léon Bottou, 2017 Proceedings of the 34th International Conference on Machine Learning (ICML), Vol. 70 (Machine Learning Research) DOI: 10.5555/3305890.3306076 - Introduces the Wasserstein GAN, detailing its theoretical foundation on the Earth Mover's distance and proposing weight clipping as the method to enforce the Lipschitz constraint on the critic.
- Improved Training of Wasserstein GANs, Ishaan Gulrajani, Faruk Ahmed, Martín Arjovsky, Vincent Dumoulin, and Aaron Courville, 2017 Advances in Neural Information Processing Systems 30 (NeurIPS 2017) (Curran Associates, Inc.) - Addresses the limitations of weight clipping in WGANs by introducing the gradient penalty, a more effective and stable regularization method for enforcing the Lipschitz constraint.
- Generative Adversarial Networks, Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, Yoshua Bengio, 2020 Communications of the ACM, Vol. 63 DOI: 10.1145/3422622 - Provides a survey of Generative Adversarial Networks, discussing their motivations, architectures, and training challenges, including the need for stability improvements like those offered by WGANs.