Maximum likelihood features for generative image models

DOI10.1214/17-AOAS1025MaRDI QIDQ1684214zbMATH OpenOpenAlexFDO

Authors Lo-Bin Chang, Eran Borenstein, Wei Zhang, Stuart Geman

Publication date 8 December 2017

Published in The Annals of Applied Statistics (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1214/17-aoas1025

zbMATH Keywords

sufficiencyfeaturescomputer visiongenerative modelsimage modelsappearance modelsconditional modeling

Mathematics Subject Classification ID

Bayesian inference (62F15) Random fields; image analysis (62M40) Image analysis in multivariate analysis (62H35)

Recommendations

• Learning a generative model of images by factoring appearance and shape
• Generative modeling of convolutional neural networks
• Fields of experts
• Object Recognition via Local Patch Labelling
• Representing and recognizing objects with massive local image patches

Cited in

(7)

• Generative modeling of convolutional neural networks
• Replicating neuroscience observations on ML/MF and AM face patches by deep generative model
• Multimodal image synthesis with conditional implicit maximum likelihood estimation
• Learning a generative model of images by factoring appearance and shape
• Intraday pairs trading strategies on high frequency data: the case of oil companies
• On the rate of convergence of image classifiers based on convolutional neural networks
• Sparse and deep generalizations of the FRAME model

This page was built for publication: Maximum likelihood features for generative image models

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1684214)