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
The Challenge of Non-Convergence
Was this section helpful?
- Generative Adversarial Networks, Ian J. Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, Yoshua Bengio, 2014 Advances in Neural Information Processing Systems, Vol. 27 (NeurIPS) - The foundational paper introducing GANs, defining the minimax objective, and establishing the connection to Jensen-Shannon Divergence, which are root causes of non-convergence discussed in the section.
- Wasserstein GAN, Martin Arjovsky, Soumith Chintala, and Léon Bottou, 2017 Proceedings of the 34th International Conference on Machine Learning (ICML), Vol. 70 - Introduces the Wasserstein distance as an alternative to JSD, directly addressing the vanishing gradient problem when distributions have negligible overlap, a key challenge detailed in the section.
- Improved Techniques for Training GANs, Tim Salimans, Ian Goodfellow, Wojciech Zaremba, Vicki Cheung, Alec Radford, Xi Chen, Xi Chen, 2016 Advances in Neural Information Processing Systems, Vol. 29 DOI: 10.48550/arXiv.1606.03498 - This paper discusses common training instabilities in GANs and proposes several practical heuristics to stabilize training, implicitly highlighting the difficulties of non-convergence and mode collapse.
- On the Convergence of Adversarial Training, Thomas Mescheder, Andreas Geiger, and Sebastian Nowozin, 2018 Proceedings of the 35th International Conference on Machine Learning (ICML), Vol. 80 (PMLR (Proceedings of Machine Learning Research)) DOI: 10.5598/v80/mescheder18a - Provides a theoretical analysis of GAN training dynamics, shedding light on the difficulties of finding saddle points and the oscillatory behavior encountered with alternating gradient updates.