American University
Browse

Aerial scene classification through fine-tuning with adaptive learning rates and label smoothing

Download (2.13 MB)
journal contribution
posted on 2023-08-05, 12:55 authored by Biserka Petrovska, Tatjana Atanasova-Pacemska, Roberto CorizzoRoberto Corizzo, P. Mignone, Petre Lameski, Eftim Zdravevski

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.

History

Publisher

Applied Sciences (Switzerland)

Notes

Applied Sciences (Switzerland), Volume 10, Issue 17, September 2020, Article number 5792.

Handle

http://hdl.handle.net/1961/auislandora:85548

Usage metrics

    Computer Science

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC