Subject: remote sensing; convolutional neural network; fine-tuning; learning rate scheduler; cyclical learning rates; label smoothing; classification accuracy
Year: 2020
Type: Article
Title: Fintech and Artificial Intelligence in Finance-Towards a transparent financialindustry”(FinAI) CA19130
Author: Petrovska, Biserka
Author: Atanasova-Pacemska, Tatjana
Author: Corizzo, Roberto
Author: Mignone, Paolo
Author: Lameski, Petre
Author: Zdravevski, Eftim
Abstract: Remote Sensing (RS) image classification has recently attracted great attention for its application in different tasks, including environmental monitoring, battlefield surveillance, and geospatial object detection. The best practices for these tasks often involve transfer learning from pre-trained Convolutional Neural Networks (CNNs). A common approach in the literature is employing CNNs for feature extraction, and subsequently train classifiers exploiting such features. In this paper, we propose the adoption of transfer learning by fine-tuning pre-trained CNNs for end-to-end aerial image classification. Our approach performs feature extraction from the fine-tuned neural networks and remote sensing image classification with a Support Vector Machine (SVM) model with linear and Radial Basis Function (RBF) kernels. To tune the learning rate hyperparameter, we employ a linear decay learning rate scheduler as well as cyclical learning rates. Moreover, in order to mitigate the overfitting problem of pre-trained models, we apply label smoothing regularization. For the fine-tuning and feature extraction process, we adopt the Inception-v3 and Xception inception-based CNNs, as well the residual-based networks ResNet50 and DenseNet121. We present extensive experiments on two real-world remote sensing image datasets: AID and NWPU-RESISC45. The results show that the proposed method exhibits classification accuracy of up to 98%, outperforming other state-of-the-art methods.
Publisher: MDPI
Relation: Applied Sciences
Identifier: oai:repository.ukim.mk:20.500.12188/22334
Identifier: http://hdl.handle.net/20.500.12188/22334
