• Home
  • Search
  • Multiscale Attention-Based Subdomain Dynamic Adaptation for Cross-Domain Scene Classification
  • Cite Icon9
  • https://doi.org/10.1109/lgrs.2024.3367623Copy DOI Icon

Multiscale Attention-Based Subdomain Dynamic Adaptation for Cross-Domain Scene Classification

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

Cross-domain scene classification is proposed to address the problems of difficult labeling of remote-sensing (RS) image datasets and poor generalization ability of supervised models, aiming to better utilize existing knowledge. To minimize the difference between the source- and target-domain distributions, many deep-domain adaptation methods have been generated, but most of them are based on the difference metric function, which only globally aligns the edge distributions without taking into account the effect of each sample on the network in different and the relationship between related subdomains in different domains of the same category, resulting in a large amount of fine-grained information being lost. In addition, existing domain adaptation methods do not adaptively balance the weights of the marginal and conditional distributions well. To overcome the above difficulties, a multiscale attention-based subdomain dynamic adaptation (SAMRA) method is proposed. The relative importance of the two is balanced by calculating the dynamic weights of each sample in the different domains to globally adjust the marginal distribution and by obtaining finer-grained key information from the subdomains to locally adjust the conditional distribution. Moreover, multiscale feature generation and attention mechanisms support the extraction of more robust features and more complete information, as well as more purposeful transfer. The results of cross-domain experiments show that the improvement of SAMRA over state-of-the-art deep-domain adaptation methods is significant.

Similar Papers
  • Research Article
  • Citations28

Attention-Based Dynamic Alignment and Dynamic Distribution Adaptation for Remote Sensing Cross-Domain Scene Classification

  • Jan 01, 2022
  • IEEE Transactions on Geoscience and Remote Sensing
  • Cong Yang +3
  • Research Article

An attention guided joint distribution domain adaptation method for fault diagnosis

  • Jun 26, 2025
  • Journal of Vibration and Control
  • Songli Tang +1
  • Research Article
  • Citations8

Cross-domain retinopathy classification with optical coherence tomography images via a novel deep domain adaptation method.

  • May 11, 2021
  • Journal of Biophotonics
  • Yuemei Luo +4
  • Research Article
  • Citations57

Attention-Based Multiscale Residual Adaptation Network for Cross-Scene Classification

  • Mar 12, 2021
  • IEEE Transactions on Geoscience and Remote Sensing
  • Sihan Zhu +3
  • Research Article
  • Citations51

A Cross-Domain Stacked Denoising Autoencoders for Rotating Machinery Fault Diagnosis Under Different Working Conditions

  • Jan 01, 2019
  • IEEE Access
  • Shan Pang +1
  • Research Article

FJDA: a feature fusion and joint distribution adaptation method for fault diagnosis based on variable working conditions

  • Aug 04, 2025
  • Measurement Science and Technology
  • Ying Zhang +2
  • Research Article
  • Citations100

Classifier-Constrained Deep Adversarial Domain Adaptation for Cross-Domain Semisupervised Classification in Remote Sensing Images

  • Aug 22, 2019
  • IEEE Geoscience and Remote Sensing Letters
  • Wenxiu Teng +4
  • Research Article
  • Citations39

A multi-constrained domain adaptation network for remaining useful life prediction of bearings

  • Nov 03, 2023
  • Mechanical Systems and Signal Processing
  • Xingjun Dong +4
  • Research Article
  • Citations45

Structure preservation and distribution alignment in discriminative transfer subspace learning

  • Feb 01, 2019
  • Neurocomputing
  • Ting Xiao +4
  • Research Article
  • Citations24

A novel joint distinct subspace learning and dynamic distribution adaptation method for fault transfer diagnosis

  • Sep 25, 2022
  • Measurement
  • Huoyao Xu +4
  • Research Article
  • Citations19

Joint Domain Adaptation Based on Adversarial Dynamic Parameter Learning

  • Aug 01, 2021
  • IEEE Transactions on Emerging Topics in Computational Intelligence
  • Yumeng Yuan +4
  • Research Article
  • Citations19

Pseudo-Label-Assisted Subdomain Adaptation for Hyperspectral Image Classification

  • Jun 01, 2024
  • IEEE Transactions on Circuits and Systems for Video Technology
  • Zhixi Feng +4
  • Conference Article
  • Citations3

Compact Cluster-based Balanced Distribution Adaptation for Transfer Learning

  • Jul 01, 2019
  • Xu Zhang +2
  • Research Article
  • Citations22

Importance-weighted conditional adversarial network for unsupervised domain adaptation

  • Apr 04, 2020
  • Expert Systems with Applications
  • Peng Liu +5
  • Research Article
  • Citations16

Adversarial domain adaptation for cross data source macromolecule in situ structural classification in cellular electron cryo-tomograms

  • Jul 01, 2019
  • Bioinformatics
  • Ruogu Lin +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.