Generative Deep Deconvolutional Learning
This addresses feature learning for image classification, but appears incremental as it builds on existing deep convolutional and deconvolutional approaches.
The paper tackles the problem of multi-layer convolutional dictionary learning by developing a generative Bayesian model with novel probabilistic pooling, achieving excellent classification results on MNIST and Caltech 101 datasets.
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.