skip to main content

SciTech ConnectSciTech Connect

Title: A Deep Generative Deconvolutional Image Model

A deep generative model is developed for representation and analysis of images, based on a hierarchical convolutional dictionary-learning framework. Stochastic unpooling is employed to link consecutive layers in the model, yielding top-down image generation. A Bayesian support vector machine is linked to the top-layer features, yielding max-margin discrimination. Deep deconvolutional inference is employed when testing, to infer the latent features, and the top-layer features are connected with the max-margin classifier for discrimination tasks. The model is efficiently trained using a Monte Carlo expectation-maximization (MCEM) algorithm; the algorithm is implemented on graphical processor units (GPU) to enable large-scale learning, and fast testing. Excellent results are obtained on several benchmark datasets, including ImageNet, demonstrating that the proposed model achieves results that are highly competitive with similarly sized convolutional neural networks.
; ; ; ;
Publication Date:
OSTI Identifier:
Report Number(s):
DOE Contract Number:
Resource Type:
Journal Article
Resource Relation:
Journal Name: Journal of Machine Learning Research, 51:741-750
Research Org:
Pacific Northwest National Laboratory (PNNL), Richland, WA (US)
Sponsoring Org:
Country of Publication:
United States
Machine learning; deep learning; dictionary learning; convolutional neural network; image analysis; image classification; factor analysis