Greedy Deep Dictionary Learning

TL;DR

This paper introduces deep dictionary learning, a multi-layer approach learned greedily layer-by-layer, demonstrating superior performance over existing deep learning and supervised dictionary learning methods on benchmark datasets.

Contribution

The paper presents a novel deep dictionary learning framework that learns multi-level dictionaries greedily, simplifying the training process and improving results.

Findings

Outperforms stacked autoencoders and deep belief networks

Achieves better results than discriminative KSVD and label consistent KSVD

Demonstrates effectiveness on benchmark datasets

Abstract

In this work we propose a new deep learning tool called deep dictionary learning. Multi-level dictionaries are learnt in a greedy fashion, one layer at a time. This requires solving a simple (shallow) dictionary learning problem, the solution to this is well known. We apply the proposed technique on some benchmark deep learning datasets. We compare our results with other deep learning tools like stacked autoencoder and deep belief network; and state of the art supervised dictionary learning tools like discriminative KSVD and label consistent KSVD. Our method yields better results than all.