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
Continuous Approximations (Gumbel-Softmax)
Was this section helpful?
- Categorical Reparameterization with Gumbel-Softmax, Eric Jang, Shixiang Gu, Ben Poole, 2016 International Conference on Learning Representations (ICLR) DOI: 10.48550/arXiv.1611.01144 - One of the two original papers introducing the Gumbel-Softmax trick for differentiable sampling from categorical distributions.
- The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables, Chris J. Maddison, Andriy Mnih, Yee Whye Teh, 2016 International Conference on Learning Representations (ICLR) DOI: 10.48550/arXiv.1611.00712 - The other seminal work, concurrently published, proposing the Concrete distribution, which is mathematically equivalent to the Gumbel-Softmax.
- Text Generation with Gumbel-Softmax, Matt J. Kusner, José Miguel Hernández-Lobato, 2017 Proceedings of the 34th International Conference on Machine Learning (ICML), Vol. 70 (PMLR (Proceedings of Machine Learning Research)) DOI: 10.48550/arXiv.1704.05814 - Demonstrates the practical application of the Gumbel-Softmax reparameterization trick for text generation, including its use in generative adversarial networks (GANs) and variational autoencoders (VAEs).