EUVIMEDEUVIMED entdecken
Crossref

Transductive Few-Shot Learning With Enhanced Spectral-Spatial Embedding for Hyperspectral Image Classification

Bobo Xi, Yun Zhang, Jiaojiao Li, Yan Huang, Yunsong Li, Zan Li, Jocelyn Chanussot

IEEE Transactions on Image Processing · 2025 · 34 · 854-868

DOI: 10.1109/tip.2025.3531709 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Image Processing, 2025. Verfasst von Bobo Xi und 6 weiteren Autor:innen. Die Arbeit wurde bisher 50-mal zitiert (Crossref) und nennt 53 Literaturangaben. Gefördert von: National Natural Science Foundation of China, China Postdoctoral Science Foundation, Natural Science Basic Research Plan in Shaanxi Province of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Few-shot learning (FSL) has been rapidly developed in the hyperspectral image (HSI) classification, potentially eliminating time-consuming and costly labeled data acquisition requirements. Effective feature embedding is empirically significant in FSL methods, which is still challenging for the HSI with rich spectral-spatial information. In addition, compared with inductive FSL, transductive models typically perform better as they explicitly leverage the statistics in the query set. To this end, we devise a transductive FSL framework with enhanced spectral-spatial embedding (TEFSL) to fully exploit the limited prior information available. First, to improve the informative features and suppress the redundant ones contained in the HSI, we devise an attentive feature embedding network (AFEN) comprising a channel calibration module (CCM). Next, a meta-feature interaction module (MFIM) is designed to optimize the support and query features by learning adaptive co-attention using convolutional filters. During inference, we propose an iterative graph-based prototype refinement scheme (iGPRS) to achieve test-time adaptation, making the class centers more representative in a transductive learning manner. Extensive experimental results on four standard benchmarks demonstrate the superiority of our model with various handfuls (i.e., from 1 to 5) labeled samples. The code will be available online at https://github.com/B-Xi/TIP_2025_TEFSL.

Förderung

  • National Natural Science Foundation of China
  • China Postdoctoral Science Foundation
  • Natural Science Basic Research Plan in Shaanxi Province of China
  • Basic and Applied Basic Research Foundation of Guangdong Province
  • Shaanxi Province Postdoctoral Science Foundation
  • Climbing Program of National Space Science Center
  • Fundamental Research Funds for the Central Universities
  • Youth Innovation Team of Shaanxi Universities

Zitieren

APA

Xi, B., Zhang, Y., Li, J., Huang, Y., Li, Y., Li, Z., & Chanussot, J. (2025). Transductive Few-Shot Learning With Enhanced Spectral-Spatial Embedding for Hyperspectral Image Classification. IEEE Transactions on Image Processing, 34, 854-868. https://doi.org/10.1109/tip.2025.3531709

Vancouver

Xi B, Zhang Y, Li J, Huang Y, Li Y, Li Z, et al. Transductive Few-Shot Learning With Enhanced Spectral-Spatial Embedding for Hyperspectral Image Classification. IEEE Transactions on Image Processing. 2025;34:854-868. doi:10.1109/tip.2025.3531709

BibTeX
@article{Xi2025,
  author = {Xi, Bobo and Zhang, Yun and Li, Jiaojiao and Huang, Yan and Li, Yunsong and Li, Zan and Chanussot, Jocelyn},
  title = {Transductive Few-Shot Learning With Enhanced Spectral-Spatial Embedding for Hyperspectral Image Classification},
  journal = {IEEE Transactions on Image Processing},
  year = {2025},
  volume = {34},
  pages = {854--868},
  doi = {10.1109/tip.2025.3531709}
}
Kostenlos starten →