Efficient Foundation Model Adaptation for Hyperspectral Image Classification Under Label Scarce Conditions
Open Access
- 1 January 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 19, 27751-27768
Abstract
No abstract availableFunding Information
- Longjiang Project Young Goose Innovation Team Support Program (2024CYLJ01)
- Natural Science Foundation of Heilongjiang Province for Key projects, China (ZD2021F004)
- Science and Technology Project of the Department of Transportation of Heilongjiang Province (No. 2025Z016)
This publication has 37 references indexed in Scilit:
- DFBSNet: Dual frequency-domain branch fusion and selection network for hyperspectral anomaly detectionPattern Recognition, 2026
- S3CRAD: Superpixel-guided background inpainting and spatial-spectral constrained representation for hyperspectral anomaly detectionOptics and Lasers in Engineering, 2026
- A query-driven twin network framework with optimization-based meta-learning for few-shot hyperspectral image classificationPattern Recognition, 2025
- Multimodal prototypical networks with Co-metric fusion for few-shot hyperspectral image classificationNeurocomputing, 2025
- Multi-level relation learning for cross-domain few-shot hyperspectral image classificationApplied Intelligence, 2024
- Strategies for dimensionality reduction in hyperspectral remote sensing: A comprehensive overviewThe Egyptian Journal of Remote Sensing and Space Sciences, 2024
- Masked Autoencoders Are Scalable Vision Learners2022
- Robust fine-tuning of zero-shot models2022
- Efficient Parametrization of Multi-domain Deep Neural Networks2018
- Recent advances in techniques for hyperspectral image processingRemote Sensing of Environment, 2009