Multiple Texture Boltzmann Machines

Jyri Kivinen, Christopher Williams
Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics, PMLR 22:638-646, 2012.

Abstract

We assess the generative power of the mPoT-model 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 texture-specific hidden unit biases. We show comparable performance of the multiple texture model to individually trained texture models.

Cite this Paper

BibTeX
@InProceedings{pmlr-v22-kivinen12, title = {Multiple Texture Boltzmann Machines}, author = {Kivinen, Jyri and Williams, Christopher}, booktitle = {Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics}, pages = {638--646}, year = {2012}, editor = {Lawrence, Neil D. and Girolami, Mark}, volume = {22}, series = {Proceedings of Machine Learning Research}, address = {La Palma, Canary Islands}, month = {21--23 Apr}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v22/kivinen12/kivinen12.pdf}, url = {https://proceedings.mlr.press/v22/kivinen12.html}, abstract = {We assess the generative power of the mPoT-model 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 texture-specific hidden unit biases. We show comparable performance of the multiple texture model to individually trained texture models.} }
Endnote
%0 Conference Paper %T Multiple Texture Boltzmann Machines %A Jyri Kivinen %A Christopher Williams %B Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2012 %E Neil D. Lawrence %E Mark Girolami %F pmlr-v22-kivinen12 %I PMLR %P 638--646 %U https://proceedings.mlr.press/v22/kivinen12.html %V 22 %X We assess the generative power of the mPoT-model 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 texture-specific hidden unit biases. We show comparable performance of the multiple texture model to individually trained texture models.
RIS
TY - CPAPER TI - Multiple Texture Boltzmann Machines AU - Jyri Kivinen AU - Christopher Williams BT - Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics DA - 2012/03/21 ED - Neil D. Lawrence ED - Mark Girolami ID - pmlr-v22-kivinen12 PB - PMLR DP - Proceedings of Machine Learning Research VL - 22 SP - 638 EP - 646 L1 - http://proceedings.mlr.press/v22/kivinen12/kivinen12.pdf UR - https://proceedings.mlr.press/v22/kivinen12.html AB - We assess the generative power of the mPoT-model 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 texture-specific hidden unit biases. We show comparable performance of the multiple texture model to individually trained texture models. ER -
APA
Kivinen, J. & Williams, C.. (2012). Multiple Texture Boltzmann Machines. Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 22:638-646 Available from https://proceedings.mlr.press/v22/kivinen12.html.

Related Material