Aug 2026
COVER-EL: Class cOVERage-Aware Noise Correction for Crowdsourced Labels via Elimination-Based Inference.
This work proposes a class coverage-aware noise correction method for crowdsourced labels via elimination-based inference (COVER-EL), and provides a probably approximately correct (PAC)-style bound that gives a high-probability guarantee on the overall error after correction.
Bi Wang, Yan-Ting Yang, Xuelian Li
· IEEE Transactions on Neural... · 0 citations