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
Disentanglement Metrics and Challenges
Was this section helpful?
- InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets, Xi Chen, Yan Duan, Rein Houthooft, John Schulman, Ilya Sutskever, Pieter Abbeel, 2016 Advances in Neural Information Processing Systems 29, Vol. 29 (Curran Associates, Inc.) - Introduces InfoGAN for learning interpretable representations and the Mutual Information Gap (MIG) metric for evaluating disentanglement.
- β-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework, Irina Higgins, Loic Matthey, Arka Pal, Christopher Burgess, Xavier Glorot, Matthew Botvinick, Alexander Lerchner, and Andrea Banino, 2017 International Conference on Learning Representations (ICLR) DOI: 10.48550/arXiv.1804.03599 - Presents Beta-VAE, a method for achieving disentangled representations by modifying the VAE objective, and discusses the trade-off between disentanglement and reconstruction quality.
- Disentangling by Factorizing, Hyunjik Kim and Andriy Mnih, 2018 International Conference on Machine Learning (ICML), Vol. 80 - Introduces FactorVAE for learning disentangled representations and the FactorVAE score as a quantitative metric.
- Towards a Better Understanding of Disentangling Representations, Francesco Locatello, Stefan Bauer, Mario Lucic, Gunnar Raetsch, Sylvain Gelly, Bernhard Schoelkopf, and Olivier Bachem, 2019 International Conference on Machine Learning (ICML), Vol. 97 - A comprehensive study that evaluates various disentanglement methods and metrics, highlighting the limitations of current approaches and the challenges in defining and measuring disentanglement.