MSAM with kernels 1-11 added to UNet skip connections yields 2.32% mIoU and 2.88% mF1 gains on hyperspectral urban driving datasets.
Adabelief optimizer: Adapting stepsizes by the belief in observed gradients,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
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.