EUVIMEDEUVIMED entdecken
Crossref

Multi-Gaussian Prototype Metric With Dual Optimization for Cross-Domain Few-Shot Hyperspectral Image Classification

Kaiyuan Shi, Xiaohua Zhang, Hongyun Meng, Chenjing Jia, Licheng Jiao

IEEE Transactions on Geoscience and Remote Sensing · 2025 · 63 · 1-19

DOI: 10.1109/tgrs.2025.3605262 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Geoscience and Remote Sensing, 2025. Verfasst von Kaiyuan Shi und 4 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 54 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Aero-Science Fund, Science and Technology Plan Project of Xi’an.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Metric-based few-shot learning (FSL) methods have shown great potential in cross-domain hyperspectral image (HSI) classification. However, existing approaches face three key challenges: First, HSIs exhibit complex spatial–spectral structures, and cross-domain distribution shifts further exacerbate feature discrepancies among same-class samples, increasing the difficulty of extracting class-consistent features. Second, in cross-domain few-shot scenarios, although some methods incorporate pseudo-label estimation to achieve class-level alignment, their effectiveness is limited by the scarcity of labeled samples in the target domain and the uncertainty of pseudo-labels, and existing domain-adversarial strategies still primarily focus on global distribution alignment, making it difficult to effectively model class-level shared features across domains. Third, intraclass feature modeling typically relies on a single class prototype, which fails to capture the complex and long-tailed distribution of intraclass features in few-shot learning scenarios. To address these challenges, a multi-Gaussian prototype metric with dual optimization (MGPDO) is proposed for cross-domain few-shot HSI classification. Specifically, for consistent feature extraction from samples with complex structures, a multiscale feature extractor is designed to obtain features at multiple scales via parallel convolutions and pyramid pooling structures. For class-level alignment, the prototype-based cyclic domain triplet loss is proposed, integrating domain-adversarial learning with cross-domain prototype contrast. The module iteratively optimizes prototype pairs to increase similarity between positive pairs and reduce correlation between negative pairs, promoting class-level alignment and shared features extraction across domains. Furthermore, for intraclass feature modeling, a multi-Gaussian prototype metric is introduced, which assigns multiple Gaussian prototypes to each class to construct a one-to-many mapping, effectively modeling complex long-tailed feature distribution and improving classification performance. Experimental results on three standard hyperspectral datasets validate the effectiveness of the proposed method, offering a novel perspective on deep learning-based cross-domain few-shot HSI classification.

Förderung

  • National Natural Science Foundation of China
  • Aero-Science Fund
  • Science and Technology Plan Project of Xi’an

Zitieren

APA

Shi, K., Zhang, X., Meng, H., Jia, C., & Jiao, L. (2025). Multi-Gaussian Prototype Metric With Dual Optimization for Cross-Domain Few-Shot Hyperspectral Image Classification. IEEE Transactions on Geoscience and Remote Sensing, 63, 1-19. https://doi.org/10.1109/tgrs.2025.3605262

Vancouver

Shi K, Zhang X, Meng H, Jia C, Jiao L. Multi-Gaussian Prototype Metric With Dual Optimization for Cross-Domain Few-Shot Hyperspectral Image Classification. IEEE Transactions on Geoscience and Remote Sensing. 2025;63:1-19. doi:10.1109/tgrs.2025.3605262

BibTeX
@article{Shi2025,
  author = {Shi, Kaiyuan and Zhang, Xiaohua and Meng, Hongyun and Jia, Chenjing and Jiao, Licheng},
  title = {Multi-Gaussian Prototype Metric With Dual Optimization for Cross-Domain Few-Shot Hyperspectral Image Classification},
  journal = {IEEE Transactions on Geoscience and Remote Sensing},
  year = {2025},
  volume = {63},
  pages = {1--19},
  doi = {10.1109/tgrs.2025.3605262}
}
Kostenlos starten →