# A Light-weight Deep Learning Model for Remote Sensing Image Classification

## TL;DR

This paper introduces a lightweight deep learning model for remote sensing image classification that uses knowledge distillation to achieve high accuracy with reduced complexity, suitable for edge devices.

## Contribution

The paper evaluates various CNN architectures and develops a compact teacher-student model that outperforms existing systems on a remote sensing benchmark.

## Key findings

- The proposed models outperform state-of-the-art systems.
- Knowledge distillation effectively reduces model complexity.
- Models are suitable for deployment on edge devices.

## Abstract

In this paper, we present a high-performance and light-weight deep learning model for Remote Sensing Image Classification (RSIC), the task of identifying the aerial scene of a remote sensing image. To this end, we first valuate various benchmark convolutional neural network (CNN) architectures: MobileNet V1/V2, ResNet 50/151V2, InceptionV3/InceptionResNetV2, EfficientNet B0/B7, DenseNet 121/201, ConNeXt Tiny/Large. Then, the best performing models are selected to train a compact model in a teacher-student arrangement. The knowledge distillation from the teacher aims to achieve high performance with significantly reduced complexity. By conducting extensive experiments on the NWPU-RESISC45 benchmark, our proposed teacher-student models outperforms the state-of-the-art systems, and has potential to be applied on a wide rage of edge devices.