Evaluating the Informativity of a Training Sample for Image Classification by Deep Learning Methods

被引：2

作者：

Rusyn, B. P. ^{[1
]}

Lutsyk, O. A. ^{[1
]}

Kosarevych, R. Y. ^{[1
]}

机构：

[1] Natl Acad Sci Ukraine, Karpenko Physicomech Inst, Lvov, Ukraine

来源：

CYBERNETICS AND SYSTEMS ANALYSIS | 2021年 / 57卷 / 06期

关键词：

deep learning; feature selection; training sample; convolutional neural network; FEATURE-SELECTION;

D O I：

10.1007/s10559-021-00411-4

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

A new approach to evaluating the informativity of a training sample when recognizing images obtained by means of remote sensing is proposed. It is shown that the informativity of a training sample can be represented by a set of characteristics, where each of them describes certain data properties. A dependence between the training sample characteristics and the accuracy of the classifier trained on the basis of this sample is established. The proposed approach is applied to various test training samples and their evaluation results are presented. When evaluating the training sample using the new approach, the process is shown to be much faster than that of training a neural network. This allows us to use the proposed approach for the preliminary estimation of a training sample in the problems of image recognition by deep learning methods.

引用

页码：853 / 863

页数：11

共 50 条

[31] Comparative Analysis of Classical Machine Learning and Deep Learning Methods for Fruit Image Recognition and Classification
Salim, Nareen O. M.
Mohammed, Ahmed Khorsheed
TRAITEMENT DU SIGNAL, 2024, 41 (03) : 1331 - 1343
[32] Evaluating deep learning models for sentiment classification
Karakus, Betul Ay
Talo, Muhammed
Hallac, Ibrahim Riza
Aydin, Galip
CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE, 2018, 30 (21):
[33] Wavelet decomposition facilitates training on small datasets for medical image classification by deep learning
Axel H. Masquelin
Nicholas Cheney
C. Matthew Kinsey
Jason H. T. Bates
Histochemistry and Cell Biology, 2021, 155 : 309 - 317
[34] Deep Learning Pre-training Strategy for Mammogram Image Classification: an Evaluation Study
Kadie Clancy
Sarah Aboutalib
Aly Mohamed
Jules Sumkin
Shandong Wu
Journal of Digital Imaging, 2020, 33 : 1257 - 1265
[35] Wavelet decomposition facilitates training on small datasets for medical image classification by deep learning
Masquelin, Axel H.
Cheney, Nicholas
Kinsey, C. Matthew
Bates, Jason H. T.
HISTOCHEMISTRY AND CELL BIOLOGY, 2021, 155 (02) : 309 - 317
[36] Deep Learning Pre-training Strategy for Mammogram Image Classification: an Evaluation Study
Clancy, Kadie
Aboutalib, Sarah
Mohamed, Aly
Sumkin, Jules
Wu, Shandong
JOURNAL OF DIGITAL IMAGING, 2020, 33 (05) : 1257 - 1265
[37] Active learning for training sample selection in remote sensing image classification using spatial information
Lu, Qikai
Ma, Yong
Xia, Gui-Song
REMOTE SENSING LETTERS, 2017, 8 (12) : 1210 - 1219
[38] Query by Image Examination: Classification of Digital Image-Based Forensics Using Deep Learning Methods
Kara, Ilker
ACTA INFOLOGICA, 2023, 7 (02): : 348 - 359
[39] Very Deep Convolutional Neural Network Based Image Classification Using Small Training Sample Size
Liu, Shuying
Deng, Weihong
PROCEEDINGS 3RD IAPR ASIAN CONFERENCE ON PATTERN RECOGNITION ACPR 2015, 2015, : 730 - 734
[40] Evaluating Pretrained Deep Learning Models for Image Classification Against Individual and Ensemble Adversarial Attacks
Rahman, Mafizur
Roy, Prosenjit
Frizell, Sherri S.
Qian, Lijun
IEEE ACCESS, 2025, 13 : 35230 - 35242

← 1 2 3 4 5 →