AusSmoke and MultiNatSmoke are new fully-labeled, geographically diverse smoke segmentation datasets that expand scale by an order of magnitude and improve model performance and generalization for wildfire detection.
Fire and smoke datasets in 20 years: An in-depth re- view
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
-
AusSmoke meets MultiNatSmoke: a fully-labelled diverse smoke segmentation dataset
AusSmoke and MultiNatSmoke are new fully-labeled, geographically diverse smoke segmentation datasets that expand scale by an order of magnitude and improve model performance and generalization for wildfire detection.