A Light-weight Deep Learning Model for Remote Sensing Image Classification
This work addresses the need for efficient aerial scene classification on resource-constrained edge devices, representing an incremental improvement in model optimization.
The paper tackles remote sensing image classification by developing a lightweight deep learning model using knowledge distillation from top-performing CNNs, achieving state-of-the-art results on the NWPU-RESISC45 benchmark with reduced complexity for edge deployment.
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.