Nov 03, 2017 (modified: Dec 06, 2017)ICLR 2018 Conference Blind Submissionreaders: everyoneShow Bibtex
Abstract:The information about class labels has been empirically shown useful in improving the sample quality of generative adversarial nets (GANs). In this paper, we mathematically study the properties of the current variants of GANs that make use of class label information. With class aware gradient and cross-entropy decomposition, we reveal how class labels and associated losses influence GAN's training. Based on that, we propose Activation Maximization Generative Adversarial Networks (AM-GAN) as an advanced solution. A set of controlled experiments have been conducted to validate our analysis and evaluate the effectiveness of our solution, where AM-GAN outperforms other strong baselines and achieves state-of-the-art Inception Score (8.91) on CIFAR-10. In addition, we demonstrate that, with the Inception ImageNet classifier, Inception Score mainly tracks the diversity of the generator, and there is, however, no reliable evidence that it can reflect the true sample quality. We thus propose a new metric, called AM Score, to provide more accurate estimation on the sample quality. Our proposed model also outperforms the baseline methods in the new metric.
TL;DR:Understand how class labels help GAN training. Propose a new evaluation metric for generative models.
Keywords:Generative Adversarial Nets, GANs, Evaluation Metrics, Generative Model, Deep Learning, Adversarial Learning, Inception Score, AM Score
Enter your feedback below and we'll get back to you as soon as possible.