A Robust and Low Complexity Deep Learning Model for Remote Sensing Image Classification

Cam Le (Vortragende:r, eingeladen), Lam Pham (Autor:in, eingeladen), Nghia NVN (Autor:in, eingeladen), Truong Nguyen (Autor:in, eingeladen), Trang Le (Autor:in, eingeladen)

Publikation: Beitrag in Buch oder TagungsbandVortrag mit Beitrag in TagungsbandBegutachtung

Abstract

In this paper, we present a robust and low complexity deep learning model for Remote Sensing Image Classification (RSIC), the task of identifying the scene of a remote sensing image. In particular, we firstly evaluate different low complexity and benchmark deep neural networks: MobileNetV1, MobileNetV2, NASNetMobile, and EfficientNetB0, which present the number of trainable parameters lower than 5 Million (M). After indicating best network architecture, we further improve the network performance by applying attention schemes to multiple feature maps extracted from middle layers of the network. To deal with the issue of increasing the model footprint as using attention schemes, we apply the quantization technique to satisfy the maximum of 20 MB memory occupation. By conducting extensive experiments on the benchmark datasets NWPU-RESISC45, we achieve a robust and low-complexity model, which is very competitive to the state-of-the-art systems and potential for real-life applications on edge devices.
OriginalspracheEnglisch
Titel8th International Conference on Intelligent Information Technology (ICIIT 2023)
Seiten1-8
Seitenumfang8
PublikationsstatusVeröffentlicht - 13 Juli 2023
VeranstaltungCIIT 2023: 2023 8th International Conference on Intelligent Information Technology - Da Nang, Vietnam
Dauer: 24 Feb. 202326 Feb. 2023

Publikationsreihe

NameProceedings of the 2023 8th International Conference on Intelligent Information Technology

Konferenz

KonferenzCIIT 2023: 2023 8th International Conference on Intelligent Information Technology
Land/GebietVietnam
StadtDa Nang
Zeitraum24/02/2326/02/23

Research Field

  • Ehemaliges Research Field - Data Science

Fingerprint

Untersuchen Sie die Forschungsthemen von „A Robust and Low Complexity Deep Learning Model for Remote Sensing Image Classification“. Zusammen bilden sie einen einzigartigen Fingerprint.

Diese Publikation zitieren