UnGAP turns aleatoric uncertainty into an active calibration signal via affine feature modulation to fix gradient suppression in heteroscedastic crack segmentation while maintaining real-time performance.
Phiseg: Capturing uncertainty in medical image segmentation
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
-
UnGAP: Uncertainty-Guided Affine Prompting for Real-Time Crack Segmentation
UnGAP turns aleatoric uncertainty into an active calibration signal via affine feature modulation to fix gradient suppression in heteroscedastic crack segmentation while maintaining real-time performance.