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
Inception Score (IS): Formulation and Limitations
Was this section helpful?
- Improved Techniques for Training GANs, Tim Salimans, Ian Goodfellow, Wojciech Zaremba, Vicki Cheung, Alec Radford, Xi Chen, 2016 Advances in Neural Information Processing Systems, Vol. 29 (Advances in Neural Information Processing Systems) DOI: 10.48550/arXiv.1606.03498 - This foundational paper introduces the Inception Score (IS) as a quantitative metric for assessing the quality and diversity of images generated by GANs.
- Rethinking the Inception Architecture for Computer Vision, Christian Szegedy, Vincent Vanhoucke, Sergey Ioffe, Jon Shlens, Zbigniew Wojna, 2016 Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (IEEE) DOI: 10.1109/CVPR.2016.36 - This paper presents the Inception-v3 neural network architecture, which is the pre-trained classifier used for calculating the Inception Score.
- GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium, Martin Heusel, Hubert Ramsauer, Thomas Unterthiner, Bernhard Nessler, Sepp Hochreiter, 2017 Advances in Neural Information Processing Systems, Vol. 30 (Curran Associates, Inc.) DOI: 10.48550/arXiv.1706.08500 - This paper introduces the Fréchet Inception Distance (FID), a widely used metric that addresses some limitations of the Inception Score by comparing generated and real data distributions.
- Are GANs Created Equal? A Large-Scale Study, Mario Lucic, Karol Kurach, Marcin Michalski, Sylvain Gelly, Olivier Bousquet, 2018 Advances in Neural Information Processing Systems, Vol. 31 DOI: 10.5591/978-1-57766-081-6.1030 - This study offers a comprehensive comparison of various GAN evaluation metrics, including the Inception Score, providing insights into their empirical performance and practical considerations.