ChangeFlow reformulates remote sensing change detection as latent rectified-flow mask synthesis, reaching 80.4% average F1 across four benchmarks with 1.3-point gain and sampling-based ensembling.
In: The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023 (2023) 2, 3, 4, 6, 7, 8
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
-
ChangeFlow -- Latent Rectified Flow for Change Detection in Remote Sensing
ChangeFlow reformulates remote sensing change detection as latent rectified-flow mask synthesis, reaching 80.4% average F1 across four benchmarks with 1.3-point gain and sampling-based ensembling.