Domain-Specific and Domain-Common Feature Enhancement for Cross-Domain Few-Shot Hyperspectral Image Classification

There is a small sample problem in hyperspectral image (HSI) classification task due to the difficulty of labeling samples. It is generally solved using a combination of few-shot learning and cross-domain method. In the paper, we propose a domain-specific and domain-common feature enhancement method...

Full description

Saved in:
Bibliographic Details
Main Authors: Gao, Wenfei, Liu, Fang, Liu, Jia, Xiao, Liang, Tang, Xu
Format: Conference Proceeding
Language:English
Subjects:
cross-domain
Data mining
domain adaptation
feature enhancement
Feature extraction
few-shot
Geoscience and remote sensing
hyperspectral image classification
Hyperspectral imaging
Labeling
Support vector machines
Task analysis
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:There is a small sample problem in hyperspectral image (HSI) classification task due to the difficulty of labeling samples. It is generally solved using a combination of few-shot learning and cross-domain method. In the paper, we propose a domain-specific and domain-common feature enhancement method for cross-domain few-shot HSI classification. It consists of a domain adaptation module and a feature enhancement module. The former is used to learn domain-specific features of both domains from the beginning of the network, and the latter is used to reduce domain differences by learning domain-common features through feature enhancement. The experimental results indicate that our proposed method performs better than the advanced classification methods.
ISSN:2153-7003
DOI:10.1109/IGARSS52108.2023.10281474