Generative Adversarial Networks (GANs): What it can generate and What it cannot?
arXiv:1804.00140
Abstract
In recent years, Generative Adversarial Networks (GANs) have received significant attention from the research community. With a straightforward implementation and outstanding results, GANs have been used for numerous applications. Despite the success, GANs lack a proper theoretical explanation. These models suffer from issues like mode collapse, non-convergence, and instability during training. To address these issues, researchers have proposed theoretically rigorous frameworks inspired by varied fields of Game theory, Statistical theory, Dynamical systems, etc. In this paper, we propose to give an appropriate structure to study these contributions systematically. We essentially categorize the papers based on the issues they raise and the kind of novelty they introduce to address them. Besides, we provide insight into how each of the discussed articles solves the concerned problems. We compare and contrast different results and put forth a summary of theoretical contributions about GANs with focus on image/visual applications. We expect this summary paper to give a bird's eye view to a person wishing to understand the theoretical progress in GANs so far.
References in corpus (32)
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
- Spectral Normalization for Generative Adversarial Networks
- GAN-based Synthetic Medical Image Augmentation for increased CNN Performance in Liver Lesion Classification
- Progressive Growing of GANs for Improved Quality, Stability, and Variation
- Improved Training of Wasserstein GANs
- Improved Techniques for Training GANs
- Which Training Methods for GANs do actually Converge?
- BEGAN: Boundary Equilibrium Generative Adversarial Networks
- Learning to Discover Cross-Domain Relations with Generative Adversarial Networks
- Adversarially Learned Inference
- f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization
- VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learning
- MMD GAN: Towards Deeper Understanding of Moment Matching Network
- Unrolled Generative Adversarial Networks
- Generative Moment Matching Networks
- Towards Principled Methods for Training Generative Adversarial Networks
- The Cramer Distance as a Solution to Biased Wasserstein Gradients
- Variational Approaches for Auto-Encoding Generative Adversarial Networks
- Stabilizing Training of Generative Adversarial Networks through Regularization
- Learning in Implicit Generative Models
- MuseGAN: Multi-track Sequential Generative Adversarial Networks for Symbolic Music Generation and Accompaniment
- AdaGAN: Boosting Generative Models
- Loss-Sensitive Generative Adversarial Networks on Lipschitz Densities
- On the regularization of Wasserstein GANs
- Adversarial Generation of Natural Language
- GP-GAN: Towards Realistic High-Resolution Image Blending
- Gradient descent GAN optimization is locally stable
- Auto-painter: Cartoon Image Generation from Sketch by Using Conditional Generative Adversarial Networks
- A Convex Duality Framework for GANs
- Memorization Precedes Generation: Learning Unsupervised GANs with Memory Networks
- Comparative Study on Generative Adversarial Networks