AI RESEARCH
QUTCC: Quantile Uncertainty Training and Conformal Calibration for Imaging Inverse Problems
arXiv CS.AI
•
ArXi:2507.14760v2 Announce Type: replace-cross While deep learning offers tremendous promise for scientific and medical imaging, any failures and hallucinations (predictions that do not coincide with reality) are hard to pinpoint and can have serious downstream consequences. Uncertainty estimation techniques, such as conformal prediction, can help by predicting statistically valid error bars for a model's prediction.