Please use this identifier to cite or link to this item:
Title: ELM embedded discriminative dictionary learning for image classification
Authors: Zeng, Yijie
Li, Yue
Chen, Jichao
Jia, Xiaofan
Huang, Guang-Bin
Keywords: Engineering::Electrical and electronic engineering
Issue Date: 2020
Source: Zeng, Y., Li, Y., Chen, J., Jia, X. & Huang, G. (2020). ELM embedded discriminative dictionary learning for image classification. Neural Networks, 123, 331-342.
Journal: Neural Networks
Abstract: Dictionary learning is a widely adopted approach for image classification. Existing methods focus either on finding a dictionary that produces discriminative sparse representation, or on enforcing priors that best describe the dataset distribution. In many cases, the dataset size is often small with large intra-class variability and nondiscriminative feature space. In this work we propose a simple and effective framework called ELM-DDL to address these issues. Specifically, we represent input features with Extreme Learning Machine (ELM) with orthogonal output projection, which enables diverse representation on nonlinear hidden space and task specific feature learning on output space. The embeddings are further regularized via a maximum margin criterion (MMC) to maximize the inter-class variance and minimize intra-class variance. For dictionary learning, we design a novel weighted class specific ℓ1,2 norm to regularize the sparse coding vectors, which promotes uniformity of the sparse patterns of samples belonging to the same class and suppresses support overlaps of different classes. We show that such regularization is robust, discriminative and easy to optimize. The proposed method is combined with a sparse representation classifier (SRC) to evaluate on benchmark datasets. Results show that our approach achieves state-of-the-art performance compared to other dictionary learning methods.
ISSN: 0893-6080
DOI: 10.1016/j.neunet.2019.11.015
Schools: School of Electrical and Electronic Engineering 
Rights: © 2019 Elsevier Ltd. All rights reserved.
Fulltext Permission: none
Fulltext Availability: No Fulltext
Appears in Collections:EEE Journal Articles

Citations 20

Updated on Sep 20, 2023

Web of ScienceTM
Citations 20

Updated on Sep 22, 2023

Page view(s)

Updated on Sep 23, 2023

Google ScholarTM




Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.