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.
- Research Organization:
- Pacific Northwest National Lab. (PNNL), Richland, WA (United States)
- Sponsoring Organization:
- USDOE
- DOE Contract Number:
- AC05-76RL01830
- OSTI ID:
- 1253859
- Report Number(s):
- PNNL-SA-115998
- Journal Information:
- Journal of Machine Learning Research, Vol. 51; ISSN 1532-4435
- Publisher:
- JMLR
- Country of Publication:
- United States
- Language:
- English
Similar Records
Boosting background suppression in the NEXT experiment through Richardson-Lucy deconvolution
Machine Learning Assisted Safety Modeling and Analysis of Advanced Reactors