Deep Dictionary Learning with An Intra-class Constraint

07/14/2022
by   Xia Yuan, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/17/2019

Class Specific or Shared? A Hybrid Dictionary Learning Network for Image Classification

Dictionary learning methods can be split into two categories: i) class s...
research
08/08/2015

Deep Boosting: Joint Feature Selection and Analysis Dictionary Learning in Hierarchy

This work investigates how the traditional image classification pipeline...
research
09/11/2018

Deep Micro-Dictionary Learning and Coding Network

In this paper, we propose a novel Deep Micro-Dictionary Learning and Cod...
research
10/23/2020

DLDL: Dynamic Label Dictionary Learning via Hypergraph Regularization

For classification tasks, dictionary learning based methods have attract...
research
12/04/2018

A multi-class structured dictionary learning method using discriminant atom selection

In the last decade, traditional dictionary learning methods have been su...
research
10/23/2020

SAHDL: Sparse Attention Hypergraph Regularized Dictionary Learning

In recent years, the attention mechanism contributes significantly to hy...
research
05/20/2020

Discriminative Dictionary Design for Action Classification in Still Images and Videos

In this paper, we address the problem of action recognition from still i...

Please sign up or login with your details

Forgot password? Click here to reset