CLPM: A Hybrid Network With Cross-Space Learning and Perception-Driven Mechanism for Long-Tailed Remote Sensing Image Classification
Long-tailed distribution is a common issue in remote sensing image classification (RSIC), and many datasets suffer from severe class imbalance. This imbalance often causes the classifier to focus on the head classes with more samples, neglecting the tail classes. As a result, the precision of the ta...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/11018338/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850118333396942848 |
|---|---|
| author | Lei Zhang Min Kong Changfeng Jing Xing Xing |
| author_facet | Lei Zhang Min Kong Changfeng Jing Xing Xing |
| author_sort | Lei Zhang |
| collection | DOAJ |
| description | Long-tailed distribution is a common issue in remote sensing image classification (RSIC), and many datasets suffer from severe class imbalance. This imbalance often causes the classifier to focus on the head classes with more samples, neglecting the tail classes. As a result, the precision of the tail classes is reduced, which in turn affects the generalization ability of the classifier. To address this problem, a hybrid network based on cross-space learning and perception-driven mechanism (CLPM) is proposed to improve the classification accuracy of samples from the tail classes. The CLPM network consists of three components. The cross-space representation learning branch is designed to enhance the representation capability of tail-class samples by integrating multiscale and multiregion spatial features. In parallel, the adaptive perception classification branch dynamically adjusts the receptive fields to improve generalization across different resolutions and challenging scenarios. In addition, the CLPM innovatively applies the von Mises-Fisher (vMF) distribution to remote sensing images for high-dimensional interclass feature modeling. Building on this, a vMF-based contrastive loss function is proposed. This approach effectively coordinates the learning processes of head and tail classes while enhancing the precision of feature representation. The effectiveness of CLPM is validated on datasets with varying balance ratios, including SIRI-WHU, CLRS, and NWPU-RESISC45. Results show that CLPM significantly improves tail classes accuracy while maintaining high recognition rates for head and middle classes. Compared with the existing methods, CLPM has significant advantages in the overall recognition accuracy, the long-tailed problem, and diversity adaptation. |
| format | Article |
| id | doaj-art-6d8ceaa3ea0a49479f37ef77a1f11541 |
| institution | OA Journals |
| issn | 1939-1404 2151-1535 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj-art-6d8ceaa3ea0a49479f37ef77a1f115412025-08-20T02:35:54ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-0118142721429010.1109/JSTARS.2025.357529211018338CLPM: A Hybrid Network With Cross-Space Learning and Perception-Driven Mechanism for Long-Tailed Remote Sensing Image ClassificationLei Zhang0https://orcid.org/0000-0002-6731-822XMin Kong1https://orcid.org/0009-0005-6808-7952Changfeng Jing2https://orcid.org/0000-0002-1270-5353Xing Xing3https://orcid.org/0009-0005-3239-2226School of Intelligent Science and Technology, Beijing University of Civil Engineering and Architecture, Beijing, ChinaSchool of Intelligent Science and Technology, Beijing University of Civil Engineering and Architecture, Beijing, ChinaSchool of Information Engineering, China University of Geosciences (Beijing), Beijing, ChinaSchool of Intelligent Science and Technology, Beijing University of Civil Engineering and Architecture, Beijing, ChinaLong-tailed distribution is a common issue in remote sensing image classification (RSIC), and many datasets suffer from severe class imbalance. This imbalance often causes the classifier to focus on the head classes with more samples, neglecting the tail classes. As a result, the precision of the tail classes is reduced, which in turn affects the generalization ability of the classifier. To address this problem, a hybrid network based on cross-space learning and perception-driven mechanism (CLPM) is proposed to improve the classification accuracy of samples from the tail classes. The CLPM network consists of three components. The cross-space representation learning branch is designed to enhance the representation capability of tail-class samples by integrating multiscale and multiregion spatial features. In parallel, the adaptive perception classification branch dynamically adjusts the receptive fields to improve generalization across different resolutions and challenging scenarios. In addition, the CLPM innovatively applies the von Mises-Fisher (vMF) distribution to remote sensing images for high-dimensional interclass feature modeling. Building on this, a vMF-based contrastive loss function is proposed. This approach effectively coordinates the learning processes of head and tail classes while enhancing the precision of feature representation. The effectiveness of CLPM is validated on datasets with varying balance ratios, including SIRI-WHU, CLRS, and NWPU-RESISC45. Results show that CLPM significantly improves tail classes accuracy while maintaining high recognition rates for head and middle classes. Compared with the existing methods, CLPM has significant advantages in the overall recognition accuracy, the long-tailed problem, and diversity adaptation.https://ieeexplore.ieee.org/document/11018338/Adaptive perception (AP)cross-space learninglong-tailed distributionremote sensing image classification (RSIC)von Mises-Fisher (vMF) distribution |
| spellingShingle | Lei Zhang Min Kong Changfeng Jing Xing Xing CLPM: A Hybrid Network With Cross-Space Learning and Perception-Driven Mechanism for Long-Tailed Remote Sensing Image Classification IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Adaptive perception (AP) cross-space learning long-tailed distribution remote sensing image classification (RSIC) von Mises-Fisher (vMF) distribution |
| title | CLPM: A Hybrid Network With Cross-Space Learning and Perception-Driven Mechanism for Long-Tailed Remote Sensing Image Classification |
| title_full | CLPM: A Hybrid Network With Cross-Space Learning and Perception-Driven Mechanism for Long-Tailed Remote Sensing Image Classification |
| title_fullStr | CLPM: A Hybrid Network With Cross-Space Learning and Perception-Driven Mechanism for Long-Tailed Remote Sensing Image Classification |
| title_full_unstemmed | CLPM: A Hybrid Network With Cross-Space Learning and Perception-Driven Mechanism for Long-Tailed Remote Sensing Image Classification |
| title_short | CLPM: A Hybrid Network With Cross-Space Learning and Perception-Driven Mechanism for Long-Tailed Remote Sensing Image Classification |
| title_sort | clpm a hybrid network with cross space learning and perception driven mechanism for long tailed remote sensing image classification |
| topic | Adaptive perception (AP) cross-space learning long-tailed distribution remote sensing image classification (RSIC) von Mises-Fisher (vMF) distribution |
| url | https://ieeexplore.ieee.org/document/11018338/ |
| work_keys_str_mv | AT leizhang clpmahybridnetworkwithcrossspacelearningandperceptiondrivenmechanismforlongtailedremotesensingimageclassification AT minkong clpmahybridnetworkwithcrossspacelearningandperceptiondrivenmechanismforlongtailedremotesensingimageclassification AT changfengjing clpmahybridnetworkwithcrossspacelearningandperceptiondrivenmechanismforlongtailedremotesensingimageclassification AT xingxing clpmahybridnetworkwithcrossspacelearningandperceptiondrivenmechanismforlongtailedremotesensingimageclassification |