arrow
Return

Large-margin representation learning for texture classification

delete2023-06-01
delete2
delete
OA
AI
J
Jonathan de Matos *
D
de Oliveira, Luiz Eduardo Soares
A
Alceu de Souza Britto
A
Alessandro L. Koerich
DOI:10.1016/j.patrec.2023.04.006delete
deleteOriginal
deleteShare
deleteSave
View PDF
Abstract

Abstract

En 中文
This paper presents a novel approach combining convolutional layers (CLs) and large-margin metric learning for training supervised models on small datasets for texture classification. The core of such an approach is a loss function that computes the distances between instances of interest and support vectors. The objective is to update the weights of CLs iteratively to learn a representation with a large margin between classes. Each iteration results in a large-margin discriminant model represented by support vectors based on such a representation. The advantage of the proposed approach w.r.t. convolutional neural networks (CNNs) is two-fold. First, it allows representation learning with a small amount of data due to the reduced number of parameters compared to an equivalent CNN. Second, it has a low training cost since the backpropagation considers only support vectors. The experimental results on texture and histopathologic image datasets show that the proposed approach achieves competitive accuracy with lower computational cost and faster convergence compared to equivalent CNNs. (c) 2023 Elsevier B.V. All rights reserved.
Keywords:
Fully convolutional networks
Large-margin classifier
Feature extraction
Texture

Journal

Pattern Recognition Letters cover
Pattern Recognition Letters
IF:
3.3
Papers:
8.0K
Citations:
2.0W

Organization

E
ecole de technologie superieure - canada
Scholars:
1.5K
Papers: 1.6K
Citations: 2.1K
U
university of quebec montreal
Scholars:
3.9K
Papers: 3.5K
Citations: 4.9K
U
university of quebec
Scholars:
206
Papers: 103
Citations: 1.2W
researcher View more organizations
Cited Papers

Cited Papers

BACH: Grand challenge on breast cancer histology images
err2019-08-01
err364
errOAAI
errAresta, Guilherme; Araujo, Teresa; Kwok, Scotty; Chennamsetty, Sai Saketh; Safwan, Mohammed; Alex, Varghese; Marami, Bahram; Prastawa, Marcel; Chan, Monica; Donovan, Michael; Fernandez, Gerardo; Zeineh, Jack; Kohl, Matthias; Walz, Christoph; Ludwig, Florian; Braunewell, Stefan; Baust, Maximilian; Quoc Dang Vu; Minh Nguyen Nhat To; Kim, Eal; Kwak, Jin Tae; Galal, Sameh; Sanchez-Freire, Veronica; Brancati, Nadia; Frucci, Maria; Riccio, Daniel; Wang, Yaqi; Sun, Lingling; Ma, Kaiqiang; Fang, Jiannan; Kone, Ismael; Boulmane, Lahsen; Campilho, Aurelio; Eloy, Catarina; Polonia, Antonio; Aguiar, Paulo
errShare
errSave
Texture Feature Extraction Methods: A Survey
err2019-01-01
err275
errOAAI
errHumeau-Heurtier, Anne
errShare
errSave
ImageNet Large Scale Visual Recognition Challenge
err2015-04-11
err2.7W
PREAI
errRussakovsky, Olga; Deng, Jia; Su, Hao; Krause, Jonathan; Satheesh, Sanjeev; Ma, Sean; Huang, Zhiheng; Karpathy, Andrej; Khosla, Aditya; Bernstein, Michael; Berg, Alexander C.; Fei-Fei, Li
errShare
errSave
Multi-class texture analysis in colorectal cancer histology
err2016-06-16
err342
errOAAI
errKather, Jakob Nikolas; Weis, Cleo-Aron; Bianconi, Francesco; Melchers, Susanne M.; Schad, Lothar R.; Gaiser, Timo; Marx, Alexander; Zoellner, Frank Gerrit
errShare
errSave
Optimising a Simple Fully Convolutional Network for Accurate Brain Age Prediction in the PAC 2019 Challenge
err2021-05-10
err26
errOAAI
errGong, Weikang; Beckmann, Christian F.; Vedaldi, Andrea; Smith, Stephen M.; Peng, Han
errShare
errSave
Review of deep learning: concepts, CNN architectures, challenges, applications, future directions
err2021-03-31
err2.9K
errOAAI
errAlzubaidi, Laith; Zhang, Jinglan; Humaidi, Amjad J.; Al-Dujaili, Ayad; Duan, Ye; Al-Shamma, Omran; Santamaria, J.; Fadhel, Mohammed A.; Al-Amidie, Muthana; Farhan, Laith
errShare
errSave
no more