Remote Sensing Image Classification with Decoupled Knowledge Distillation

TL;DR

This paper introduces a lightweight remote sensing image classification method using decoupled knowledge distillation and G-GhostNet backbone, achieving high accuracy with significantly fewer parameters suitable for resource-limited devices.

Contribution

The paper proposes a novel lightweight classification approach combining G-GhostNet and decoupled knowledge distillation for improved efficiency and accuracy.

Findings

Achieves nearly the same accuracy as VGG-16 with 6.24 times fewer parameters.

Demonstrates effectiveness on RSOD and AID datasets.

Balances model size and performance effectively.

Abstract

To address the challenges posed by the large number of parameters in existing remote sensing image classification models, which hinder deployment on resource-constrained devices, this paper proposes a lightweight classification method based on knowledge distillation. Specifically, G-GhostNet is adopted as the backbone network, leveraging feature reuse to reduce redundant parameters and significantly improve inference efficiency. In addition, a decoupled knowledge distillation strategy is employed, which separates target and non-target classes to effectively enhance classification accuracy. Experimental results on the RSOD and AID datasets demonstrate that, compared with the high-parameter VGG-16 model, the proposed method achieves nearly equivalent Top-1 accuracy while reducing the number of parameters by 6.24 times. This approach strikes an excellent balance between model size and classification performance, offering an efficient solution for deployment on resource-limited devices.