Learning a Generative Model of Images by Factoring Appearance and Shape

DOI10.1162/NECO_a_00086zbMath1209.68564WikidataQ51893244 ScholiaQ51893244MaRDI QIDQ3085328

Jamie Shotton, John Winn, Nicolas Le Roux, Nicolas Heess

Publication date: 31 March 2011

Published in: Neural Computation (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1162/neco_a_00086

zbMATH Keywords

computer vision; layer-based and hierarchical models; low-level generative models; masked RBMs; restricted Boltzmann machines (RBMs)

Mathematics Subject Classification ID

68T05: Learning and adaptive systems in artificial intelligence

65D18: Numerical aspects of computer graphics, image analysis, and computational geometry

68T45: Machine vision and scene understanding

Related Items

The shape Boltzmann machine: a strong model of object shape, Training restricted Boltzmann machines: an introduction

Cites Work

• Modeling visual patterns by integrating descriptive and generative methods
• Occlusion models for natural images: A statistical study of a scale-invariant dead leaves model
• Topographic Independent Component Analysis
• A Stochastic Grammar of Images
• Training Products of Experts by Minimizing Contrastive Divergence
• Greedy Learning of Multiple Objects in Images Using Robust Statistics and Factorial Learning
• A Fast Learning Algorithm for Deep Belief Nets