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
StackGAN: Text-to-Image Synthesis
Was this section helpful?
- StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks, Han Zhang, Tao Xu, Hongsheng Li, Shaoting Zhang, Xiaogang Wang, Xiaolei Huang, Dimitris N. Metaxas, 2017 2017 IEEE International Conference on Computer Vision (IEEE) DOI: 10.1109/ICCV.2017.394 - Presents the original two-stage StackGAN architecture for generating high-resolution images from text descriptions, introducing conditioning augmentation.
- StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks, Han Zhang, Tao Xu, Hongxu Ma, Zhiming Liu, Gang Huang, Shaoting Zhang, and Dimitris Metaxas, 2018 International Conference on Learning Representations (ICLR) (OpenReview.net) DOI: 10.48550/arXiv.1710.05465 - Extends the original StackGAN by improving training stability, loss functions, and generator architecture for enhanced text-to-image synthesis.
- Conditional Generative Adversarial Nets, Mehdi Mirza and Simon Osindero, 2014 arXiv preprint arXiv:1411.1784 DOI: 10.48550/arXiv.1411.1784 - Introduces the concept of conditional GANs, allowing generation of images based on specific conditions like class labels, a precursor to text-to-image generation.
- Generative Adversarial Nets, Ian J. Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron C. Courville, Yoshua Bengio, 2014 Advances in Neural Information Processing Systems, Vol. 27 (NeurIPS) DOI: 10.48550/arXiv.1406.2661 - This paper introduces Generative Adversarial Networks, a core component of StackGAN and other advanced generation models.