Multi-Scale Graph-Based Feature Fusion for Few-Shot Remote Sensing Image Scene Classification
Remote sensing image scene classification has drawn extensive attention for its wide application in various scenarios. Scene classification in many practical cases faces the challenge of few-shot conditions. The major difficulty of few-shot remote sensing image scene classification is how to extract...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-11-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/21/5550 |
| _version_ | 1827645580966363136 |
|---|---|
| author | Nan Jiang Haowen Shi Jie Geng |
| author_facet | Nan Jiang Haowen Shi Jie Geng |
| author_sort | Nan Jiang |
| collection | DOAJ |
| description | Remote sensing image scene classification has drawn extensive attention for its wide application in various scenarios. Scene classification in many practical cases faces the challenge of few-shot conditions. The major difficulty of few-shot remote sensing image scene classification is how to extract effective features from insufficient labeled data. To solve these issues, a multi-scale graph-based feature fusion (MGFF) model is proposed for few-shot remote sensing image scene classification. In the MGFF model, a graph-based feature construction model is developed to transform traditional image features into graph-based features, which aims to effectively represent the spatial relations among images. Then, a graph-based feature fusion model is proposed to integrate graph-based features of multiple scales, which aims to enhance sample discrimination based on different scale information. Experimental results on two public remote sensing datasets prove that the MGFF model can achieve superior accuracy than other few-shot scene classification approaches. |
| first_indexed | 2024-03-09T18:41:11Z |
| format | Article |
| id | doaj.art-8cf9dadc80bb4d8cab0fa1a4645b1060 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T18:41:11Z |
| publishDate | 2022-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-8cf9dadc80bb4d8cab0fa1a4645b10602023-11-24T06:40:49ZengMDPI AGRemote Sensing2072-42922022-11-011421555010.3390/rs14215550Multi-Scale Graph-Based Feature Fusion for Few-Shot Remote Sensing Image Scene ClassificationNan Jiang0Haowen Shi1Jie Geng2School of Electronics and Information, Northwestern Polytechnical University, Xi’an 710072, ChinaSchool of Electronics and Information, Northwestern Polytechnical University, Xi’an 710072, ChinaSchool of Electronics and Information, Northwestern Polytechnical University, Xi’an 710072, ChinaRemote sensing image scene classification has drawn extensive attention for its wide application in various scenarios. Scene classification in many practical cases faces the challenge of few-shot conditions. The major difficulty of few-shot remote sensing image scene classification is how to extract effective features from insufficient labeled data. To solve these issues, a multi-scale graph-based feature fusion (MGFF) model is proposed for few-shot remote sensing image scene classification. In the MGFF model, a graph-based feature construction model is developed to transform traditional image features into graph-based features, which aims to effectively represent the spatial relations among images. Then, a graph-based feature fusion model is proposed to integrate graph-based features of multiple scales, which aims to enhance sample discrimination based on different scale information. Experimental results on two public remote sensing datasets prove that the MGFF model can achieve superior accuracy than other few-shot scene classification approaches.https://www.mdpi.com/2072-4292/14/21/5550few-shot learninggraph-based featuremulti-scale feature fusionremote sensing image scene classification |
| spellingShingle | Nan Jiang Haowen Shi Jie Geng Multi-Scale Graph-Based Feature Fusion for Few-Shot Remote Sensing Image Scene Classification Remote Sensing few-shot learning graph-based feature multi-scale feature fusion remote sensing image scene classification |
| title | Multi-Scale Graph-Based Feature Fusion for Few-Shot Remote Sensing Image Scene Classification |
| title_full | Multi-Scale Graph-Based Feature Fusion for Few-Shot Remote Sensing Image Scene Classification |
| title_fullStr | Multi-Scale Graph-Based Feature Fusion for Few-Shot Remote Sensing Image Scene Classification |
| title_full_unstemmed | Multi-Scale Graph-Based Feature Fusion for Few-Shot Remote Sensing Image Scene Classification |
| title_short | Multi-Scale Graph-Based Feature Fusion for Few-Shot Remote Sensing Image Scene Classification |
| title_sort | multi scale graph based feature fusion for few shot remote sensing image scene classification |
| topic | few-shot learning graph-based feature multi-scale feature fusion remote sensing image scene classification |
| url | https://www.mdpi.com/2072-4292/14/21/5550 |
| work_keys_str_mv | AT nanjiang multiscalegraphbasedfeaturefusionforfewshotremotesensingimagesceneclassification AT haowenshi multiscalegraphbasedfeaturefusionforfewshotremotesensingimagesceneclassification AT jiegeng multiscalegraphbasedfeaturefusionforfewshotremotesensingimagesceneclassification |