A Deep Generative Deconvolutional Image Model
Duke University
arXiv:1512.07344 [cs.CV], (23 Dec 2015)
@article{pu2015deep,
title={A Deep Generative Deconvolutional Image Model},
author={Pu, Yunchen and Yuan, Xin and Stevens, Andrew and Li, Chunyuan and Carin, Lawrence},
year={2015},
month={dec},
archivePrefix={"arXiv"},
primaryClass={cs.CV}
}
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, with implementation on graphical processor units (GPUs) for efficient 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.
December 31, 2015 by hgpu
