TY - GEN
T1 - A Robust and Low Complexity Deep Learning Model for Remote Sensing Image Classification
A2 - Le, Cam
A2 - Pham, Lam
A2 - NVN, Nghia
A2 - Nguyen, Truong
A2 - Le, Trang
PY - 2023/7/13
Y1 - 2023/7/13
N2 - 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.
AB - 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.
M3 - Conference Proceedings with Oral Presentation
SN - 978-1-4503-9961-6
T3 - Proceedings of the 2023 8th International Conference on Intelligent Information Technology
SP - 1
EP - 8
BT - 8th International Conference on Intelligent Information Technology (ICIIT 2023)
T2 - CIIT 2023: 2023 8th International Conference on Intelligent Information Technology
Y2 - 24 February 2023 through 26 February 2023
ER -