Image Quality Assessment Techniques Show Improved Training and Evaluation of Autoencoder Generative Adversarial Networks
arXiv:1708.02237
Abstract
We propose a training and evaluation approach for autoencoder Generative Adversarial Networks (GANs), specifically the Boundary Equilibrium Generative Adversarial Network (BEGAN), based on methods from the image quality assessment literature. Our approach explores a multidimensional evaluation criterion that utilizes three distance functions: an score, the Gradient Magnitude Similarity Mean (GMSM) score, and a chrominance score. We show that each of the different distance functions captures a slightly different set of properties in image space and, consequently, requires its own evaluation criterion to properly assess whether the relevant property has been adequately learned. We show that models using the new distance functions are able to produce better images than the original BEGAN model in predicted ways.
10 pages, 7 figures, 2 tables
References in corpus (15)
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- Conditional Image Synthesis With Auxiliary Classifier GANs
- Gradient Magnitude Similarity Deviation: A Highly Efficient Perceptual Image Quality Index
- Improved Techniques for Training GANs
- InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets
- Energy-based Generative Adversarial Network
- BEGAN: Boundary Equilibrium Generative Adversarial Networks
- A note on the evaluation of generative models
- Variational Approaches for Auto-Encoding Generative Adversarial Networks
- Adversarial Training Methods for Semi-Supervised Text Classification
- Learning in Implicit Generative Models
- Generative Face Completion
- GP-GAN: Towards Realistic High-Resolution Image Blending
- Multi-View Image Generation from a Single-View
- Gang of GANs: Generative Adversarial Networks with Maximum Margin Ranking