A self-supervised temporal ordering objective plus a pivot score detects persistent, non-seasonal changes in satellite time series with AUROC 0.876.
xBD: A Dataset for Assessing Building Damage from Satellite Imagery, 2019
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
OPTIMUS: Observing Persistent Transformations in Multi-temporal Unlabeled Satellite-data
A self-supervised temporal ordering objective plus a pivot score detects persistent, non-seasonal changes in satellite time series with AUROC 0.876.