A Generative Model for Deep Convolutional Learning
This addresses feature learning in image classification, though it appears incremental as it builds on existing deep convolutional and dictionary learning frameworks.
The paper developed a generative model for deep convolutional dictionary learning by integrating a novel probabilistic pooling operation, enabling efficient bottom-up pretraining and top-down refinement. Experimental results showed excellent classification performance on MNIST and Caltech 101 datasets.
A generative model is developed for deep (multi-layered) convolutional dictionary learning. A novel probabilistic pooling operation is integrated into the deep model, yielding efficient bottom-up (pretraining) and top-down (refinement) probabilistic learning. Experimental results demonstrate powerful capabilities of the model to learn multi-layer features from images, and excellent classification results are obtained on the MNIST and Caltech 101 datasets.