• Home
  • Search
  • Heterogeneous Few-shot Learning with Knowledge Distillation for Hyperspectral Image Classification
  • Cite Icon8
  • https://doi.org/10.1109/iccece54139.2022.9712772Copy DOI Icon

Heterogeneous Few-shot Learning with Knowledge Distillation for Hyperspectral Image Classification

  • Jan 14, 2022
  • Yanfang Hu +3 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Hyperspectral image (HSI) classification is one of the most popular applications in remote sensing. In practice, due to the high cost of manual labeling, only a few hyperspectral image samples with labels can be obtained. A small number of labeled training samples tend to overfit the deep network method, resulting in a sharp decline in classification accuracy. In order to solve this problem, this paper proposes a classification method for hyperspectral images based on knowledge distillation and heterogeneous few-shot learning. Firstly, the model pretrain the feature extraction network on miniImageNet, a small sample natural image dataset with abundant labeled images, and introduces knowledge distillation to improve the feature expression capability of shallow network in small sample. Then, effective knowledge transfer is carried out between two heterogeneous data sets, and the weights obtained from the model on the natural data set are transferred to the backbone network of hyperspectral image classification to improve the accuracy of HSI classification. Finally, the classifier is fine-tuned on HSI using the paradigm of small sample learning to extract discriminative hyperspectral image features and further enhance the model's detail expression. Experimental results on two hyperspectral image classification datasets show that the proposed method can effectively improve the accuracy of small sample hyperspectral image classification.

Similar Papers
  • Research Article
  • Citations748

SVM- and MRF-Based Method for Accurate Classification of Hyperspectral Images

  • Oct 01, 2010
  • IEEE Geoscience and Remote Sensing Letters
  • Yuliya Tarabalka +3
  • Research Article
  • Citations185

Heterogeneous Transfer Learning for Hyperspectral Image Classification Based on Convolutional Neural Network

  • Dec 05, 2019
  • IEEE Transactions on Geoscience and Remote Sensing
  • Xin He +2
  • Conference Article
  • Citations6

Spectral-spatial classification of hyperspectral images based on multifractal features

  • Oct 14, 2020
  • Dmitry V Uchaev +2
  • Research Article
  • Citations69

Heterogeneous Few-Shot Learning for Hyperspectral Image Classification

  • Jan 01, 2022
  • IEEE Geoscience and Remote Sensing Letters
  • Yan Wang +7
  • PDF
  • Research Article
  • Citations158

A Hyperspectral Image Classification Method Using Multifeature Vectors and Optimized KELM

  • Jan 01, 2021
  • IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
  • Huayue Chen +4
  • Book Chapter
  • Citations5

A Fast Region Growing Based Superpixel Segmentation for Hyperspectral Image Classification

  • Jan 01, 2019
  • Qianqian Xu +3
  • Research Article
  • Citations8

Semi-Supervised anchor graph ensemble for large-scale hyperspectral image classification

  • Mar 04, 2022
  • International Journal of Remote Sensing
  • Ziping He +5
  • PDF
  • Research Article
  • Citations24

Combining Spectral Unmixing and 3D/2D Dense Networks with Early-Exiting Strategy for Hyperspectral Image Classification

  • Feb 29, 2020
  • Remote Sensing
  • Bei Fang +2
  • PDF
  • Research Article
  • Citations14

Small Sample Hyperspectral Image Classification Method Based on Dual-Channel Spectral Enhancement Network

  • Aug 13, 2022
  • Electronics
  • Songwei Pei +2
  • Research Article
  • Citations10

Hyperspectral Image Classification Based on Multilevel Joint Feature Extraction Network

  • Jan 01, 2021
  • IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
  • Xiaochen Lu +4
  • Conference Article
  • Citations1

Hyperspectral Image Classification Using 3D Attention Mechanism in Collaboration with Transformer

  • Sep 22, 2023
  • Yubing Wang +2
  • PDF
  • Research Article
  • Citations42

A Lightweight 1-D Convolution Augmented Transformer with Metric Learning for Hyperspectral Image Classification.

  • Mar 03, 2021
  • Sensors
  • Xiang Hu +4
  • Research Article
  • Citations26

Hyperspectral remote sensing image classification based on residual generative Adversarial Neural Networks

  • Jul 28, 2023
  • Signal Processing
  • Bo Feng +3
  • PDF
  • Research Article
  • Citations37

Hyperspectral Image Classification with Multi-Scale Feature Extraction

  • Mar 05, 2019
  • Remote Sensing
  • Bing Tu +4
  • Research Article
  • Citations1

HZSCM: Hyperspectral Image Zero-Shot Classification via Vision-Language Models

  • Jan 01, 2025
  • IEEE Transactions on Geoscience and Remote Sensing
  • Lingbo Huang +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.