A deep generative deconvolutional image model

Published

Conference Paper

Copyright 2016 by the authors. 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.

Duke Authors

Cited Authors

  • Pu, Y; Yuan, X; Stevens, A; Li, C; Carin, L

Published Date

  • January 1, 2016

Published In

  • Proceedings of the 19th International Conference on Artificial Intelligence and Statistics, Aistats 2016

Start / End Page

  • 741 - 750

Citation Source

  • Scopus