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
Gradient Penalty (WGAN-GP)
Was this section helpful?
- Improved Training of Wasserstein GANs, Ishaan Gulrajani, Faruk Ahmed, Martin Arjovsky, Vincent Dumoulin, Aaron Courville, 2017 Advances in Neural Information Processing Systems (NeurIPS) (Curran Associates, Inc.) DOI: 10.5555/3157382.3157640 - The foundational paper introducing the gradient penalty as a method to enforce the Lipschitz constraint in Wasserstein GANs, significantly improving training stability over weight clipping.
- Wasserstein GAN, Martin Arjovsky, Soumith Chintala, Léon Bottou, 2017 International Conference on Learning Representations (ICLR) DOI: 10.48550/arXiv.1701.07875 - This paper introduced the Wasserstein GAN and the Earth Mover's distance for GAN training, highlighting the issues with original GAN loss and proposing weight clipping, which WGAN-GP later improved upon.
- Generative Deep Learning: Teaching Machines to Paint, Write, Compose, and Play, David Foster, 2019 (O'Reilly Media) - Provides a comprehensive and practical overview of generative models, including conceptual and implementation details for WGAN and WGAN-GP.
- Autograd mechanics, PyTorch Team, 2024 (PyTorch) - Essential documentation for understanding how automatic differentiation, including higher-order gradients required for the gradient penalty, works in PyTorch.