Resilience is a perturbation-based uncertainty measure for NCA segmentation that outperforms baselines in identifying low-quality predictions on medical imaging benchmarks.
In: international conference on machine learn- ing
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Conditional flow matching produces segmentation samples whose pixel-wise variance quantifies aleatoric uncertainty in medical images by learning an exact density rather than relying on stochastic diffusion sampling.
citing papers explorer
-
Measuring Prediction Uncertainty in Neural Cellular Automata
Resilience is a perturbation-based uncertainty measure for NCA segmentation that outperforms baselines in identifying low-quality predictions on medical imaging benchmarks.
-
Aleatoric Uncertainty Medical Image Segmentation Estimation via Flow Matching
Conditional flow matching produces segmentation samples whose pixel-wise variance quantifies aleatoric uncertainty in medical images by learning an exact density rather than relying on stochastic diffusion sampling.