HyperFM is a new efficient hyperspectral foundation model using spectral grouping and hybrid attention that shows performance gains on cloud property retrieval tasks from PACE data, accompanied by the release of the HyperFM250K dataset.
Self- supervised material and texture representation learning for remote sensing tasks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
HyperFM: An Efficient Hyperspectral Foundation Model with Spectral Grouping
HyperFM is a new efficient hyperspectral foundation model using spectral grouping and hybrid attention that shows performance gains on cloud property retrieval tasks from PACE data, accompanied by the release of the HyperFM250K dataset.