Automated Evolutionary Design of CNN Classifiers for Object Recognition on Satellite Images

被引：3

作者：

Polonskaia, Iana S. ^{[1
]}

Aliev, Ilya R. ^{[1
]}

Nikitin, Nikolay O. ^{[1
]}

机构：

[1] ITMO Univ, 49 Kronverksky Pr, St Petersburg 197101, Russia

来源：

10TH INTERNATIONAL YOUNG SCIENTISTS CONFERENCE IN COMPUTATIONAL SCIENCE (YSC2021) | 2021年 / 193卷

关键词：

evolutionary learning; NAS; CNN; genetic programming; machine learning; recognition; satellite images; ARCHITECTURES;

D O I：

10.1016/j.procs.2021.10.021

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

In the paper, the automated evolutionary approach FEDOT-NAS for the design of convolutional neural networks is proposed. It allows building object recognition models for remote sensing tasks. The comparison of the proposed approach with state-of-the-art tools for neural architecture search is conducted for several examples of satellite-related datasets. The results of the experiments confirm the correctness and effectiveness of the proposed approach. The implementation of FEDOT-NAS is available as an opensource tool. 2021 The Authors. Published by Elsevier B.V. Peer-review under responsibility of the scientific committee of the 10th International Young Scientists Conference on Computational Science

引用

页码：210 / 219

页数：10

共 50 条

[1] An evolutionary multi-agent system for object recognition in satellite images
Miu, HS
Leung, KS
Leung, Y
CEC: 2003 CONGRESS ON EVOLUTIONARY COMPUTATION, VOLS 1-4, PROCEEDINGS, 2003, : 520 - 527
[2] An Evolution of CNN Object Classifiers on Low-Resolution Images
Kabir, Mohsin
Ohi, Abu Quwsar
Rahman, Saifur
Mridha, M. F.
2020 IEEE 17TH INTERNATIONAL CONFERENCE ON SMART COMMUNITIES: IMPROVING QUALITY OF LIFE USING ICT, IOT AND AI (IEEEHONET 2020), 2020, : 209 - 213
[3] CIRCULAR OBJECT RECOGNITION FROM SATELLITE IMAGES
Taud, Hind
Carlos Herrera-Lozada, Juan
Antonio Alvarez-Cedillo, Jesus
Marciano-Melchor, Magdalena
Silva-Ortigoza, Ramon
Olguin-Carbajal, Mauricio
2012 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS), 2012, : 2324 - 2327
[4] Point process and CNN for small object detection in satellite images
Mabon, Jules
Ortner, Mathias
Zerubia, Josiane
IMAGE AND SIGNAL PROCESSING FOR REMOTE SENSING XXVIII, 2022, 12267
[5] Generic Object Recognition Using Both Illustration Images and Real-Object Images by CNN
Watabe, Hirokazu
Imono, Misako
Tsuchiya, Seiji
ADVANCES IN ARTIFICIAL INTELLIGENCE AND APPLIED COGNITIVE COMPUTING, 2021, : 141 - 145
[6] Surface Object Recognition with CNN and SVM in Landsat 8 Images
Ishii, Tomohiro
Nakamura, Ryosuke
Nakada, Hidemoto
Mochizuki, Yoshihiko
Ishikawa, Hiroshi
2015 14TH IAPR INTERNATIONAL CONFERENCE ON MACHINE VISION APPLICATIONS (MVA), 2015, : 341 - 344
[7] Evolutionary design of neural network classifiers for radar target recognition
Li, Y
Jiao, LC
2001 CIE INTERNATIONAL CONFERENCE ON RADAR PROCEEDINGS, 2001, : 1047 - 1049
[8] OBJECT CLASSIFIERS FOR TEXTURED IMAGES
PALUBINSKAS, G
COMPUTER ANALYSIS OF IMAGES AND PATTERNS, 1989, : 141 - 147
[9] Automated design of CNN architecture based on efficient evolutionary search
Xie, Yirong
Chen, Hong
Ma, Yongjie
Xu, Yang
NEUROCOMPUTING, 2022, 491 : 160 - 171
[10] Optimization Of Convolutional Neural Network For Object Recognition On Satellite Images
Khryashchev, V. V.
Pavlov, V. A.
Ostrovskaya, A. A.
Semenov, A. S.
2018 SYSTEMS OF SIGNAL SYNCHRONIZATION, GENERATING AND PROCESSING IN TELECOMMUNICATIONS (SYNCHROINFO), 2018,

← 1 2 3 4 5 →