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
Video Generation and Prediction
Was this section helpful?
- Video Generative Adversarial Networks, Carl Vondrick, Hamed Pirsiavash, Antonio Torralba, 2016 Advances in Neural Information Processing Systems, Vol. 29 (Curran Associates, Inc.) DOI: 10.48550/arXiv.1609.02612 - This paper introduced 3D convolutional networks into the GAN framework for generating video sequences.
- DVD-GAN: A Differentiable Video Discriminator for Training Conditional GANs, Alexia Clark, Anna Lucic, Kosta Derpanis, Marcus Brubaker, 2019 Advances in Neural Information Processing Systems, Vol. 32 (NeurIPS) - Introduces a hierarchical GAN approach with multiple discriminators to improve spatio-temporal realism and diversity in video generation.
- Assessing Generative Models via Fréchet Video Distance, Mehdi Sajjadi, Oleksiy Lukashenko, Anil Sharma, Bernhard Schölkopf, 2018 Proceedings of the 35th International Conference on Machine Learning (ICML), Vol. 80 - This paper defines Fréchet Video Distance (FVD), a metric that quantifies the quality and temporal consistency of generated video content.
- Deep multi-scale video prediction beyond mean square error, Michael Mathieu, Camille Couprie, Yann LeCun, 2016 International Conference on Learning Representations (ICLR) (OpenReview.net) DOI: 10.48550/arXiv.1511.05440 - An early application of adversarial learning to video prediction, yielding sharper future frame predictions than traditional L2 loss.