• Home
  • Search
  • Scene Classification Through Knowledge Distillation Enabled Parameter-Free Attention Model for Remote Sensing Images
  • https://doi.org/10.1109/msn57253.2022.00077Copy DOI Icon

Scene Classification Through Knowledge Distillation Enabled Parameter-Free Attention Model for Remote Sensing Images

  • Dec 1, 2022
  • Yubing Han +4 more
Show More
  • Abstract
  • Literature Map
  • References
  • Similar Papers
Abstract

Remote sensing image scene classification is to label remote sensing images as a specific scene category by understanding the semantic information of the images. It is an essential link in remote sensing image analysis and interpretation and has important research value. Convolutional neural networks (CNNs) have been dominant in remote sensing image scene classification due to their powerful feature extraction capabilities. The general trend has been to make deeper and wider CNN architectures to achieve higher classification accuracy. However, these advances to improve accuracy enlarge the network, creating too many parameters and high computational costs. Large models are difficult to deploy on resource-constrained edge devices for practical applications. Furthermore, CNNs can effectively capture local information but are weak in extracting global features. To overcome these drawbacks, we propose a novel knowledge distillation (KD) based method by employing Swin Transformer as a teacher network for guiding MobileNetV2 with Parameter-Free Attention (MobileNetV2-PFA). First, we modify MobileNetV2 by introducing PFA into the inverted bottleneck block; this improvement helps the model learn more latent and robust features without extra parameters. Second, Swin Transformer is an excellent architecture for capturing long-range dependencies via shifted window-based attention. So, we utilize the long-range dependency information from the Swin Transformer to assist MobileNetV2-PFA training through KD. Experimental results on the challenging NWPU-RESISC45 dataset show that the proposed method outperforms the original MobileNetV2 in classification accuracy with low computational consumption.

Similar Papers
  • Research Article
  • Citations46

A Supervised Progressive Growing Generative Adversarial Network for Remote Sensing Image Scene Classification

  • Jan 01, 2022
  • IEEE Transactions on Geoscience and Remote Sensing
  • Ailong Ma +4
  • Research Article
  • Citations49

A Multi-Branch Feature Fusion Strategy Based on an Attention Mechanism for Remote Sensing Image Scene Classification

  • May 17, 2021
  • Remote Sensing
  • Cuiping Shi +2
  • Conference Article
  • Citations2

Level merging attention based on dense network for remote sensing image scene classification

  • Nov 15, 2023
  • Zhi Li +3
  • PDF
  • Research Article
  • Citations13

Remote Sensing Image Scene Classification by Multiple Granularity Semantic Learning

  • Jan 01, 2022
  • IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
  • Weilong Guo +7
  • Research Article
  • Citations53

IORN: An Effective Remote Sensing Image Scene Classification Framework

  • Nov 01, 2018
  • IEEE Geoscience and Remote Sensing Letters
  • Jue Wang +4
  • Research Article
  • Citations50

An End-to-End Local-Global-Fusion Feature Extraction Network for Remote Sensing Image Scene Classification

  • Dec 13, 2019
  • Remote Sensing
  • Yafei Lv +4
  • PDF
  • Research Article
  • Citations22

Attack Selectivity of Adversarial Examples in Remote Sensing Image Scene Classification

  • Jan 01, 2020
  • IEEE Access
  • Li Chen +7
  • PDF
  • Research Article
  • Citations74

Deep Learning for Remote Sensing Image Scene Classification: A Review and Meta-Analysis

  • Oct 02, 2023
  • Remote Sensing
  • Aakash Thapa +3
  • Research Article
  • Citations21

Deep learning techniques for remote sensing image scene classification: A comprehensive review, current challenges, and future directions

  • May 01, 2023
  • Concurrency and Computation: Practice and Experience
  • Monika Kumari +1
  • Research Article
  • Citations16

A Scene Images Diversity Improvement Generative Adversarial Network for Remote Sensing Image Scene Classification

  • Dec 05, 2019
  • IEEE Geoscience and Remote Sensing Letters
  • Xin Pan +2
  • Book Chapter

ADVANCEMENTS AND CHALLENGES OF REAL-TIME DATA IN REMOTE SENSING SCENE CLASSIFICATION WITH DEEP LEARNING TECHNIQUES

  • Dec 24, 2024
  • P Deepan +4
  • Research Article
  • Citations214

Scale-Free Convolutional Neural Network for Remote Sensing Scene Classification

  • Sep 01, 2019
  • IEEE Transactions on Geoscience and Remote Sensing
  • Jie Xie +3
  • Research Article
  • Citations46

A Self-Supervised-Driven Open-Set Unsupervised Domain Adaptation Method for Optical Remote Sensing Image Scene Classification and Retrieval

  • Jan 01, 2023
  • IEEE Transactions on Geoscience and Remote Sensing
  • Siyuan Wang +2
  • PDF
  • Research Article
  • Citations24

Remote Sensing Image Scene Classification with Noisy Label Distillation

  • Jul 24, 2020
  • Remote Sensing
  • Rui Zhang +6
  • Research Article
  • Citations6

FCCNet: Surface Defects Identification of Hot Rolled Strip Based on Lightweight Convolutional Neural Network

  • Dec 15, 2023
  • ISIJ International
  • Kun Lu +6
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.