Efficient Unsupervised Clustering of Hyperspectral Images via Flexible Multi-Anchor Graphs
Unsupervised hyperspectral image (HSI) clustering is a fundamental yet challenging task due to high dimensionality and complex spectral–spatial characteristics. In this paper, we propose a novel and efficient clustering framework centered on adaptive and diverse anchor graph modeling. First, we intr...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-07-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/17/15/2647 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849765947406024704 |
|---|---|
| author | Yihong Li Ting Wang Zhe Cao Haonan Xin Rong Wang |
| author_facet | Yihong Li Ting Wang Zhe Cao Haonan Xin Rong Wang |
| author_sort | Yihong Li |
| collection | DOAJ |
| description | Unsupervised hyperspectral image (HSI) clustering is a fundamental yet challenging task due to high dimensionality and complex spectral–spatial characteristics. In this paper, we propose a novel and efficient clustering framework centered on adaptive and diverse anchor graph modeling. First, we introduce a parameter-free construction strategy that employs Entropy Rate Superpixel (ERS) segmentation to generate multiple anchor graphs of varying sizes from a single HSI, overcoming the limitation of fixed anchor quantities and enhancing structural expressiveness. Second, we propose an anchor-to-pixel label propagation mechanism to transfer anchor-level cluster labels back to the pixel level, reinforcing spatial coherence and spectral discriminability. Third, we perform clustering directly at the anchor level, which substantially reduces computational cost while retaining structure-aware accuracy. Extensive experiments on three benchmark datasets (Trento, Salinas, and Pavia Center) demonstrate the effectiveness and efficiency of our approach. |
| format | Article |
| id | doaj-art-5de4cd0cdfd745c1b06f82f15a1fed8f |
| institution | DOAJ |
| issn | 2072-4292 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj-art-5de4cd0cdfd745c1b06f82f15a1fed8f2025-08-20T03:04:43ZengMDPI AGRemote Sensing2072-42922025-07-011715264710.3390/rs17152647Efficient Unsupervised Clustering of Hyperspectral Images via Flexible Multi-Anchor GraphsYihong Li0Ting Wang1Zhe Cao2Haonan Xin3Rong Wang4Rocket Force University of Engineering, Xi’an 710025, ChinaThe School of Artificial Intelligence, Optics and Electronics (iOPEN), Northwestern Polytechnical University, Xi’an 710072, ChinaThe School of Artificial Intelligence, Optics and Electronics (iOPEN), Northwestern Polytechnical University, Xi’an 710072, ChinaThe School of Artificial Intelligence, Optics and Electronics (iOPEN), Northwestern Polytechnical University, Xi’an 710072, ChinaThe School of Artificial Intelligence, Optics and Electronics (iOPEN), Northwestern Polytechnical University, Xi’an 710072, ChinaUnsupervised hyperspectral image (HSI) clustering is a fundamental yet challenging task due to high dimensionality and complex spectral–spatial characteristics. In this paper, we propose a novel and efficient clustering framework centered on adaptive and diverse anchor graph modeling. First, we introduce a parameter-free construction strategy that employs Entropy Rate Superpixel (ERS) segmentation to generate multiple anchor graphs of varying sizes from a single HSI, overcoming the limitation of fixed anchor quantities and enhancing structural expressiveness. Second, we propose an anchor-to-pixel label propagation mechanism to transfer anchor-level cluster labels back to the pixel level, reinforcing spatial coherence and spectral discriminability. Third, we perform clustering directly at the anchor level, which substantially reduces computational cost while retaining structure-aware accuracy. Extensive experiments on three benchmark datasets (Trento, Salinas, and Pavia Center) demonstrate the effectiveness and efficiency of our approach.https://www.mdpi.com/2072-4292/17/15/2647hyperspectral image clusteringanchor graph modelingunsupervised learningERS segmentationlabel propagationefficient clustering |
| spellingShingle | Yihong Li Ting Wang Zhe Cao Haonan Xin Rong Wang Efficient Unsupervised Clustering of Hyperspectral Images via Flexible Multi-Anchor Graphs Remote Sensing hyperspectral image clustering anchor graph modeling unsupervised learning ERS segmentation label propagation efficient clustering |
| title | Efficient Unsupervised Clustering of Hyperspectral Images via Flexible Multi-Anchor Graphs |
| title_full | Efficient Unsupervised Clustering of Hyperspectral Images via Flexible Multi-Anchor Graphs |
| title_fullStr | Efficient Unsupervised Clustering of Hyperspectral Images via Flexible Multi-Anchor Graphs |
| title_full_unstemmed | Efficient Unsupervised Clustering of Hyperspectral Images via Flexible Multi-Anchor Graphs |
| title_short | Efficient Unsupervised Clustering of Hyperspectral Images via Flexible Multi-Anchor Graphs |
| title_sort | efficient unsupervised clustering of hyperspectral images via flexible multi anchor graphs |
| topic | hyperspectral image clustering anchor graph modeling unsupervised learning ERS segmentation label propagation efficient clustering |
| url | https://www.mdpi.com/2072-4292/17/15/2647 |
| work_keys_str_mv | AT yihongli efficientunsupervisedclusteringofhyperspectralimagesviaflexiblemultianchorgraphs AT tingwang efficientunsupervisedclusteringofhyperspectralimagesviaflexiblemultianchorgraphs AT zhecao efficientunsupervisedclusteringofhyperspectralimagesviaflexiblemultianchorgraphs AT haonanxin efficientunsupervisedclusteringofhyperspectralimagesviaflexiblemultianchorgraphs AT rongwang efficientunsupervisedclusteringofhyperspectralimagesviaflexiblemultianchorgraphs |