A Conformal Prediction Score that is Robust to Label Noise

arXiv:2405.02648v1 Announce Type: new
Abstract: Conformal Prediction (CP) quantifies network uncertainty by building a small prediction set with a pre-defined probability that the correct class is within this set. In this study we tackle the problem of CP calibration based on a validation set with noisy labels. We introduce a conformal score that is robust to label noise. The noise-free conformal score is estimated using the noisy labeled data and the noise level. In the test phase the noise-free score …

abstract arxiv building calibration class cs.ai cs.cv cs.lg labels network noise prediction probability robust set small study type uncertainty validation