LGAICVMLAug 5, 2017

Inception Score, Label Smoothing, Gradient Vanishing and -log(D(x)) Alternative

arXiv:1708.01729v319 citations
AI Analysis

This is an incremental theoretical study that provides mathematical insights into existing GAN issues, primarily relevant for researchers in generative models.

The paper mathematically analyzes several GAN-related topics, such as Inception Score, label smoothing, gradient vanishing, and the -log(D(x)) alternative, but does not present new experimental results or concrete numerical findings.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes