DEQ-Unmix is a deep equilibrium model for hyperspectral unmixing that uses implicit differentiation for constant-memory training and a trainable conv net to capture spectral-spatial features, showing superior performance on synthetic and real datasets.
Title resolution pending
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
-
A Deep Equilibrium Network for Hyperspectral Unmixing
DEQ-Unmix is a deep equilibrium model for hyperspectral unmixing that uses implicit differentiation for constant-memory training and a trainable conv net to capture spectral-spatial features, showing superior performance on synthetic and real datasets.