UniCD unifies supervised, weakly-supervised, and unsupervised change detection via a shared encoder and collaborative branches, claiming large accuracy gains in low-supervision settings on datasets like LEVIR-CD.
Remote sensing image change detection with transform- ers.IEEE Transactions on Geoscience and Remote Sens- ing, 60:1–14
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
-
Bridging Supervision Gaps: A Unified Framework for Remote Sensing Change Detection
UniCD unifies supervised, weakly-supervised, and unsupervised change detection via a shared encoder and collaborative branches, claiming large accuracy gains in low-supervision settings on datasets like LEVIR-CD.