Inception Score, Label Smoothing, Gradient Vanishing and -log(D(x)) Alternative
arXiv:1708.01729
Abstract
In this article, we mathematically study several GAN related topics, including Inception score, label smoothing, gradient vanishing and the -log(D(x)) alternative. --- An advanced version is included in arXiv:1703.02000 "Activation Maximization Generative Adversarial Nets". Please refer Section 6 in 1703.02000 for detailed analysis on Inception Score, and refer its appendix for the discussions on Label Smoothing, Gradient Vanishing and -log(D(x)) Alternative.
arXiv commentAn advanced version is included in arXiv:1703.02000 "Activation Maximization Generative Adversarial Nets"
References in corpus (9)
- Auto-Encoding Variational Bayes
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- Energy-based Generative Adversarial Network
- BEGAN: Boundary Equilibrium Generative Adversarial Networks
- Unrolled Generative Adversarial Networks
- Mode Regularized Generative Adversarial Networks
- Deep Directed Generative Models with Energy-Based Probability Estimation
- Geometric GAN
- Distributional Adversarial Networks