Multiple Texture Boltzmann Machines

9 years 10 months ago
Multiple Texture Boltzmann Machines
We assess the generative power of the mPoTmodel of [10] with tiled-convolutional weight sharing as a model for visual textures by specifically training on this task, evaluating model performance on texture synthesis and inpainting tasks using quantitative metrics. We also analyze the relative importance of the mean and covariance parts of the mPoT model by comparing its performance to those of its subcomponents, tiled-convolutional versions of the PoT/FoE and Gaussian-Bernoulli restricted Boltzmann machine (GB-RBM). Our results suggest that while state-of-the-art or better performance can be achieved using the mPoT, similar performance can be achieved with the mean-only model. We then develop a model for multiple textures based on the GB-RBM, using a shared set of weights but texturespecific hidden unit biases. We show comparable performance of the multiple texture model to individually trained texture models.
Jyri J. Kivinen, Christopher K. I. Williams
Added 27 Sep 2012
Updated 27 Sep 2012
Type Journal
Year 2012
Where JMLR
Authors Jyri J. Kivinen, Christopher K. I. Williams
Comments (0)