Learning sparse FRAME models for natural image patterns

DOI10.1007/S11263-014-0757-XMaRDI QIDQ1799970zbMATH OpenOpenAlexWikidataFDO

Authors Jianwen Xie, Wenze Hu, Song-Chun Zhu, Ying Nian Wu

Publication date 19 October 2018

Published in International Journal of Computer Vision (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/s11263-014-0757-x

zbMATH Keywords

Markov random fieldsgenerative modelsshared sparse coding

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Image processing (compression, reconstruction, etc.) in information and communication theory (94A08)

Recommendations

• Sparse and deep generalizations of the FRAME model
• Unsupervised learning of compositional sparse code for natural image representation
• Sparse modeling for image and vision processing
• From information scaling of natural images to regimes of statistical models
• Fields of experts

Cites work

• scientific article; zbMATH DE number 3567782 (Why is no real title available?)
• scientific article; zbMATH DE number 845714 (Why is no real title available?)
• scientific article; zbMATH DE number 1391397 (Why is no real title available?)
• $rm K$-SVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse Representation
• 10.1162/jmlr.2003.4.7-8.1235
• A Fast Learning Algorithm for Deep Belief Nets
• A stochastic grammar of images
• Algorithms for simultaneous sparse approximation. I: Greedy pursuit
• Analysis versus synthesis in signal priors
• Atomic decomposition by basis pursuit
• Composition systems
• Double Sparsity: Learning Sparse Dictionaries for Sparse Signal Approximation
• Exploratory Projection Pursuit
• Fields of experts
• From Sparse Solutions of Systems of Equations to Sparse Modeling of Signals and Images
• LIBLINEAR: a library for large linear classification
• Matching pursuits with time-frequency dictionaries
• On the convergence of markovian stochastic algorithms with rapidly decreasing ergodicity rates
• SIFT
• Simulating normalizing constants: From importance sampling to bridge sampling to path sampling
• Sparse and redundant representations. From theory to applications in signal and image processing.
• Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images
• Support union recovery in high-dimensional multivariate regression
• The cosparse analysis model and algorithms
• Training Products of Experts by Minimizing Contrastive Divergence
• Unsupervised learning of compositional sparse code for natural image representation

Cited in

(3)

• Inducing wavelets into random fields via generative boosting
• Fields of experts
• Sparse and deep generalizations of the FRAME model

Describes a project that uses

Uses Software

• Caltech-256
• SIFT
• darch
• PDCO
• LIBLINEAR

This page was built for publication: Learning sparse FRAME models for natural image patterns

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1799970)