QUTCC: Quantile Uncertainty Training and Conformal Calibration for Imaging Inverse Problems 事件

QUTCC: Quantile Uncertainty Training and Conformal Calibration for Imaging Inverse Problems arXiv:2507.14760v2 Announce Type: replace-cross Abstract: 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 f