• Home
  • Search
  • Remote Sensing Image Scene Classification Using Multiscale Feature Fusion Covariance Network With Octave Convolution
  • Cite Icon75
  • https://doi.org/10.1109/tgrs.2022.3160492Copy DOI Icon

Remote Sensing Image Scene Classification Using Multiscale Feature Fusion Covariance Network With Octave Convolution

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

In remote sensing scene classification (RSSC), features can be extracted with different spatial frequencies where high-frequency features usually represent detailed information and low-frequency features usually represent global structures. However, it is challenging to extract meaningful semantic information for RSSC tasks by just utilizing high- or low-frequency features. The spatial composition of remote sensing images (RSIs) is more complex than that of natural images, and the scales of objects vary significantly. In this article, a multiscale feature fusion covariance network (MF<sup>2</sup>CNet) with octave convolution (Oct Conv) is proposed, which can extract multifrequency and multiscale features from RSIs. First, the multifrequency feature extraction (MFE) module is used to obtain fine-grained frequency features by Oct Conv. Then, the features of different layers in MF<sup>2</sup>CNet are fused by the multiscale feature fusion (MF<sup>2</sup>) module. Finally, instead of using global average pooling (GAP), global covariance pooling (GCP) extracts high-order information from RSIs to capture richer statistics of deep features. In the proposed MF<sup>2</sup>CNet, the obtained multifrequency and multiscale features can effectively improve the performance of CNNs. Experimental results on four public RSI datasets show that MF<sup>2</sup>CNet has advantages in RSSC over current state-of-the-art methods. The source codes of this method can be found at <uri>https://github.com/liuqingxin-chd/MF2CNet</uri>.

Similar Papers
  • PDF
  • Research Article
  • Citations18

Lightweight Channel Attention and Multiscale Feature Fusion Discrimination for Remote Sensing Scene Classification

  • Jan 01, 2021
  • IEEE Access
  • Huiyao Wan +7
  • PDF
  • Research Article
  • Citations7

Evaluation of Ten Deep-Learning-Based Out-of-Distribution Detection Methods for Remote Sensing Image Scene Classification

  • Apr 24, 2024
  • Remote Sensing
  • Sicong Li +4
  • PDF
  • Research Article
  • Citations119

Enhanced Feature Pyramid Network With Deep Semantic Embedding for Remote Sensing Scene Classification

  • Jan 05, 2021
  • IEEE Transactions on Geoscience and Remote Sensing
  • Xin Wang +3
  • PDF
  • Research Article
  • Citations11

Self-Attention Network With Joint Loss for Remote Sensing Image Scene Classification

  • Jan 01, 2020
  • IEEE Access
  • Honglin Wu +4
  • PDF
  • Research Article
  • Citations117

Multi-scale Adaptive Feature Fusion Network for Semantic Segmentation in Remote Sensing Images

  • Mar 09, 2020
  • Remote Sensing
  • Ronghua Shang +5
  • PDF
  • Research Article
  • Citations41

Object Detection in Remote Sensing Images Based on Adaptive Multi-Scale Feature Fusion Method

  • Mar 04, 2024
  • Remote Sensing
  • Chun Liu +3
  • PDF
  • Research Article
  • Citations17

Multi-Scale Graph-Based Feature Fusion for Few-Shot Remote Sensing Image Scene Classification

  • Nov 03, 2022
  • Remote Sensing
  • Nan Jiang +2
  • Research Article
  • Citations4

Label Embedding Based on Interclass Correlation Mining for Remote Sensing Image Scene Classification

  • Jan 01, 2024
  • IEEE Geoscience and Remote Sensing Letters
  • Jiang He +4
  • Research Article
  • Citations105

Learning Deep Cross-Modal Embedding Networks for Zero-Shot Remote Sensing Image Scene Classification

  • Jan 14, 2021
  • IEEE Transactions on Geoscience and Remote Sensing
  • Yansheng Li +3
  • Research Article
  • Citations73

Multigranularity Decoupling Network With Pseudolabel Selection for Remote Sensing Image Scene Classification

  • Jan 01, 2023
  • IEEE Transactions on Geoscience and Remote Sensing
  • Wang Miao +2
  • PDF
  • Research Article
  • Citations15

Aggregating Features From Dual Paths for Remote Sensing Image Scene Classification

  • Jan 01, 2022
  • IEEE Access
  • Donghang Yu +5
  • PDF
  • Research Article
  • Citations25

A Multi-Scale Approach for Remote Sensing Scene Classification Based on Feature Maps Selection and Region Representation

  • Oct 25, 2019
  • Remote Sensing
  • Jun Zhang +4
  • Research Article
  • Citations32

EFCOMFF-Net: A Multiscale Feature Fusion Architecture With Enhanced Feature Correlation for Remote Sensing Image Scene Classification

  • Jan 01, 2023
  • IEEE Transactions on Geoscience and Remote Sensing
  • Junsong Chen +3
  • Research Article
  • Citations7

Remote Sensing Scene Classification via Second-Order Differentiable Token Transformer Network

  • Jan 01, 2024
  • IEEE Transactions on Geoscience and Remote Sensing
  • Kang Ni +4
  • Research Article
  • Citations10

Fusing Deep Features by Kernel Collaborative Representation for Remote Sensing Scene Classification

  • Jan 01, 2021
  • IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
  • Xiaoning Chen +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.