A masked evidential loss lets a U-Net predict forest height with calibrated per-pixel uncertainty under sparse labels, matching deterministic accuracy on the TreeUQ benchmark.
In: Advances in Neural Information Processing Systems (2020)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Deep Evidential Regression for Sparse Forest Height Estimation from Multimodal Satellite Imagery
A masked evidential loss lets a U-Net predict forest height with calibrated per-pixel uncertainty under sparse labels, matching deterministic accuracy on the TreeUQ benchmark.