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.
Urban scene understanding via hyperspectral images: Dataset and benchmark,
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.CV 3representative citing papers
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.
MSAM with kernels 1-11 added to UNet skip connections yields 2.32% mIoU and 2.88% mF1 gains on hyperspectral urban driving datasets.
citing papers explorer
-
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.
-
Multi-Scale Spectral Attention Module-based Hyperspectral Segmentation in Autonomous Driving Scenarios
MSAM with kernels 1-11 added to UNet skip connections yields 2.32% mIoU and 2.88% mF1 gains on hyperspectral urban driving datasets.