RSCNet adaptively selects task-relevant hyperspectral bands under cross-source guidance and performs attention-based fusion to achieve higher accuracy and lower complexity than prior multi-source remote sensing classifiers on three benchmarks.
Recent advances of hyperspectral imaging technology and applications in agriculture,
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
LQE is a physics-constrained learnable dimensionality reduction technique that improves average mIoU in hyperspectral urban segmentation on three datasets while using only 12-36 parameters.
The work identifies bands at 497 nm, 607 nm, and 895 nm that deliver large gains in material dissimilarity and perceptual separability on the H-City dataset compared with RGB.
citing papers explorer
-
Representative Spectral Correlation Network for Multi-source Remote Sensing Image Classification
RSCNet adaptively selects task-relevant hyperspectral bands under cross-source guidance and performs attention-based fusion to achieve higher accuracy and lower complexity than prior multi-source remote sensing classifiers on three benchmarks.
-
Learnable Quantum Efficiency Filters for Urban Hyperspectral Segmentation
LQE is a physics-constrained learnable dimensionality reduction technique that improves average mIoU in hyperspectral urban segmentation on three datasets while using only 12-36 parameters.
-
CSNR and JMIM Based Spectral Band Selection for Reducing Metamerism in Urban Driving
The work identifies bands at 497 nm, 607 nm, and 895 nm that deliver large gains in material dissimilarity and perceptual separability on the H-City dataset compared with RGB.