• Home
  • Search
  • Cross-domain few-shot hyperspectral image classification based on circle loss and dense graph convolution
  • Cite Icon1
  • https://doi.org/10.1080/01431161.2025.2538833Copy DOI Icon

Cross-domain few-shot hyperspectral image classification based on circle loss and dense graph convolution

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

ABSTRACT Deep learning methods have demonstrated exceptional performance in hyperspectral image classification in recent years. Manual annotation is costly in practical applications of hyperspectral images, leading to a scarcity of labelled samples. At the same time, hyperspectral image classification faces challenges such as spectral variations within the object and identical spectra for different objects. However, current hyperspectral image classification methods are unable to extract spectral and spatial contextual features. Under few-shot conditions, the extracted features do not provide adequate discriminative power for both intra-class and inter-class samples. Moreover, traditional few-shot classification methods require the source and target domain data to have similar distributions in the feature space; otherwise, knowledge learned from the source domain cannot effectively transfer to the target domain. To address these shortcomings, we propose enhancing the feature extraction network’s capability to capture contextual features better, improving the discrimination between intra-class and inter-class samples through contrastive learning, and utilizing graph-structured information to alleviate domain shift issues in this paper. We propose a novel few-shot hyperspectral image classification framework (CDFSL-DGCCL) in which a circle contrastive loss function is introduced to reduce the similarity between features of different classes in the target domain and increase the similarity within the same class, thereby optimizing the feature extraction network. We propose a learning strategy combining dense graph convolutional networks and the circle contrastive loss function. Two densely connected graph convolutional networks are used to extract graph-structured information from the source and target domains, and the circle contrastive loss function is employed to optimize the feature similarity with graph-structured information. A new Global Context Module (GC-RCM) is embedded into the feature extraction network (SSCRNet) to capture global spectral and spatial contextual information. Experiments on four publicly available hyperspectral image datasets demonstrate that our method outperforms existing approaches. The code is available at https://github.com/GJINGKANG/CDFSL-DGCCL.

Similar Papers
  • Conference Article
  • Citations7

Source-Free Domain Adaptation for Cross-Scene Hyperspectral Image Classification

  • Jul 17, 2022
  • Zun Xu +3
  • Research Article
  • Citations40

Physically Constrained Transfer Learning Through Shared Abundance Space for Hyperspectral Image Classification

  • Aug 21, 2020
  • IEEE Transactions on Geoscience and Remote Sensing
  • Ying Qu +5
  • Research Article
  • Citations32

Cross-Domain Few-Shot Learning Based on Graph Convolution Contrast for Hyperspectral Image Classification

  • Jan 01, 2024
  • IEEE Transactions on Geoscience and Remote Sensing
  • Zhen Ye +4
  • Book Chapter
  • Citations1

Efficient Deep Belief Network Based Hyperspectral Image Classification

  • Jan 01, 2017
  • Atif Mughees +1
  • Research Article
  • Citations156

Active multi-kernel domain adaptation for hyperspectral image classification

  • Oct 13, 2017
  • Pattern Recognition
  • Cheng Deng +3
  • Research Article
  • Citations12

Graph-Based Domain Adaptation Few-Shot Learning for Hyperspectral Image Classification

  • Feb 18, 2023
  • Remote Sensing
  • Yanbing Xu +4
  • Research Article
  • Citations32

Attention Multisource Fusion-Based Deep Few-Shot Learning for Hyperspectral Image Classification

  • Jan 01, 2021
  • IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
  • Xuejian Liang +2
  • Research Article
  • Citations66

Few-Shot Hyperspectral Image Classification Based on Adaptive Subspaces and Feature Transformation

  • Jan 01, 2022
  • IEEE Transactions on Geoscience and Remote Sensing
  • Jing Bai +6
  • Conference Article
  • Citations4

Feature Integration-Based Training for Cross-Domain Hyperspectral Image Classification

  • Jul 17, 2022
  • Cheng Zhang +2
  • Research Article
  • Citations35

Prototype-Based Multisource Domain Adaptation.

  • Oct 01, 2022
  • IEEE Transactions on Neural Networks and Learning Systems
  • Lihua Zhou +4
  • Research Article
  • Citations13

Robust Hyperspectral Image Domain Adaptation With Noisy Labels

  • Jul 01, 2019
  • IEEE Geoscience and Remote Sensing Letters
  • Wei Wei +5
  • Research Article
  • Citations7

Cross-Domain Distribution Calibration of Hyperspectral Image Classification

  • Jan 01, 2024
  • IEEE Geoscience and Remote Sensing Letters
  • Junyuan Ding +2
  • Research Article
  • Citations6

Unsupervised meta-learning with domain adaptation based on a multi-task reconstruction-classification network for few-shot hyperspectral image classification

  • Jun 20, 2024
  • Journal of Information and Intelligence
  • Yu Liu +3
  • Conference Article
  • Citations18

Few-Shot Hyperspectral Image Classification Through Multitask Transfer Learning

  • Sep 01, 2019
  • Ying Qu +2
  • Research Article
  • Citations16

Hyperspectral Image Classification Based on Unsupervised Heterogeneous Domain Adaptation CycleGan

  • Jul 01, 2020
  • Chinese Journal of Electronics
  • Xuesong Wang +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.