A reference-free metric that compares keep and erase views of competing masks with a frozen vision-language judge can audit annotation quality and reveal class-dependent ground-truth distortion in remote sensing segmentation.
Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) , pages =
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
-
Contrastive Mask Fidelity: Reference-Free Auditing of Ground-Truth Masks in Remote Sensing Semantic Segmentation
A reference-free metric that compares keep and erase views of competing masks with a frozen vision-language judge can audit annotation quality and reveal class-dependent ground-truth distortion in remote sensing segmentation.