SVMs multi-class loss feedback based discriminative dictionary learning for image classification. (April 2021)

• Record Type: Journal Article
• Authors: Yang, Bao-Qing; Guan, Xin-Ping; Zhu, Jun-Wu; Gu, Chao-Chen; Wu, Kai-Jie; Xu, Jia-Jie
• Is Part Of: Pattern recognition. Volume 112(2021)
• Publication Date: 2021-04
• Subjects: Dictionary learning -- Feature representation -- Feature learning -- Feedback learning -- Image classification; 00-01 -- 99-00; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2020.107690
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: Inspired by the feedback mechanism in cybernetics, a novel discriminative dictionary learning framework, named support vector machines (SVMs) multi-class loss feedback based discriminative dictionary learning (SMLFDL) is proposed to learn a dictionary while training SVMs. As far as we know, it is the first time that the feedback mechanism in cybernetics is adopted for constructing dictionary learning model. SMLFDL further employ the Fisher discrimination criterion on the coding coefficients under -norm constraint to make the coding coefficients have small intra-class scatter but big inter-class scatter for countering intra-class variability of datasets. An efficient and practical SMLFDL optimization algorithm is presented to learn a dictionary while training SVMs. Experimental results on several widely used image databases show that SMLFDL can achieve a competitive performance with other state-of-the-art methods on classification task. Abstract: The learning model has been popular recently due to its promising results in various image classification tasks. Many existing learning methods, especially the deep learning methods, need a large amount of training data to achieve a high accuracy of classification. Conversely, only provided with a small-size dataset, some dictionary learning (DL) methods can achieve a perfect performance on a image classification task and hence still get a lot of attention. Among these DL methods, DL based feature learning methods are the mainstream for image classification in recent years, however, most of these methods have trained a classifier independently from dictionary learning. Therefore, the features extracted by the learned dictionary may not be very proper to perform classification for the classifier. Inspired by the feedback mechanism in cybernetics, this paper proposes a novel discriminative DL framework, named support vector machines (SVMs) multi-class loss feedback based discriminative dictionary learning (SMLFDL) that learns a discriminative dictionary while training SVMs to make the features extracted by the learned dictionary and SVMs better matched with each other. Because of integrating dictionary learning and SVMs training into a unified learning framework and good exactness of the looped multi-class loss term formulated from the feedback viewpoint for the classification scheme, better classification performance can be achieved. Experimental results on several widely used image databases show that SMLFDL can achieve a competitive performance with other state-of-the-art dictionary learning methods.