Generative Deep Deconvolutional Learning

Abstract

A generative Bayesian model is developed for deep (multi-layer) convolutional dictionary learning. A novel probabilistic pooling operation is integrated into the deep model, yielding efficient bottom-up and top-down probabilistic learning. After learning the deep convolutional dictionary, testing is implemented via deconvolutional inference. To speed up this inference, a new statistical approach is proposed to project the top-layer dictionary elements to the data level. Following this, only one layer of deconvolution is required during testing. Experimental results demonstrate powerful capabilities of the model to learn multi-layer features from images. Excellent classification results are obtained on both the MNIST and Caltech 101 datasets.

21 pages, 9 figures, revised version for ICLR 2015

References in corpus (2)

• Stochastic Pooling for Regularization of Deep Convolutional Neural Networks
• Fast Inference in Sparse Coding Algorithms with Applications to Object Recognition

Cited by in corpus (2)

• Variational Autoencoder for Deep Learning of Images, Labels and Captions
• Adversarial Symmetric Variational Autoencoder