Deep Dictionary Learning with An Intra-class Constraint

TL;DR

This paper introduces a deep dictionary learning model with intra-class constraints that enhances discriminative power for visual classification by promoting intra-class compactness in representations.

Contribution

It proposes a novel deep dictionary learning framework with intra-class constraints and a layer-wise greedy optimization during classification, improving discriminative features.

Findings

Outperforms state-of-the-art methods on four image datasets.

Intra-class constraints improve representation discriminability.

Layer-wise greedy optimization is effective during classification.

Abstract

In recent years, deep dictionary learning (DDL)has attracted a great amount of attention due to its effectiveness for representation learning and visual recognition.~However, most existing methods focus on unsupervised deep dictionary learning, failing to further explore the category information.~To make full use of the category information of different samples, we propose a novel deep dictionary learning model with an intra-class constraint (DDLIC) for visual classification. Specifically, we design the intra-class compactness constraint on the intermediate representation at different levels to encourage the intra-class representations to be closer to each other, and eventually the learned representation becomes more discriminative.~Unlike the traditional DDL methods, during the classification stage, our DDLIC performs a layer-wise greedy optimization in a similar way to the training stage. Experimental results on four image datasets show that our method is superior to the state-of-the-art methods.