2016
DOI: 10.1007/s00500-016-2247-2
|View full text |Cite
|
Sign up to set email alerts
|

SVM or deep learning? A comparative study on remote sensing image classification

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

3
123
1
3

Year Published

2017
2017
2024
2024

Publication Types

Select...
7
1

Relationship

0
8

Authors

Journals

citations
Cited by 228 publications
(130 citation statements)
references
References 24 publications
3
123
1
3
Order By: Relevance
“…The amount of data (of varying quality) which is being generated every day grows tremendously in the majority of scientific and B Jakub Nalepa jakub.nalepa@polsl.pl Michal Kawulok michal.kawulok@polsl.pl 1 Institute of Informatics, Silesian University of Technology, Akademicka 16, 44-100 Gliwice, Poland engineering domains, including, among others, medical imaging, text categorization, computational biology, genomics and banking. Although it may appear quite beneficial at the first glance-more data could mean more possibilities of extracting and revealing useful underlying knowledge-training SVMs from extremely large and difficult datasets became a pivotal issue due to the high time and memory complexity of the SVM training (Liu et al 2016;Qiu et al 2016).…”
Section: Introductionmentioning
confidence: 99%
“…The amount of data (of varying quality) which is being generated every day grows tremendously in the majority of scientific and B Jakub Nalepa jakub.nalepa@polsl.pl Michal Kawulok michal.kawulok@polsl.pl 1 Institute of Informatics, Silesian University of Technology, Akademicka 16, 44-100 Gliwice, Poland engineering domains, including, among others, medical imaging, text categorization, computational biology, genomics and banking. Although it may appear quite beneficial at the first glance-more data could mean more possibilities of extracting and revealing useful underlying knowledge-training SVMs from extremely large and difficult datasets became a pivotal issue due to the high time and memory complexity of the SVM training (Liu et al 2016;Qiu et al 2016).…”
Section: Introductionmentioning
confidence: 99%
“…Недоліки методу:  модель SVM відносить новий приклад до тієї чи іншої категорії, що робить її не ймовірнісною, а лише бінарним класифікатором [19];…”
Section: метод опорних векторівunclassified
“…У праці [19] порівняно метод глибинного навчання на основі розрідженого автокодувальника (sparse auto-encoders) та SVM для класифікації супутникових знімків. Отримані результати свідчать про те, що SVM варто використовувати у випадку нестачі навчальних даних.…”
Section: методи класифікації земного покриву на основі «великих» обсяunclassified
“…With the twoclass problem, training samples ( ) are given, where ∈ is the feature vector of the given sample and is the label of its class, (+1 and -1 point to the two classes which are benign and malign classes respectively). SVM builds an optimal hyper-plane that maximizes the margin to classify the samples [24].…”
Section: Classificationmentioning
confidence: 99%
“…The most direct form is making a comparison between deep learning architectures and support vector machine (SVM) in processing audio, images and videos. However, there are not enough studies to choose the parameters once using deep learning technique for regression and classification tasks [1]- [5].…”
Section: Introductionmentioning
confidence: 99%