发帖
雷达卡
Me-Momentum: Extracting Hard Confident Examples
from Noisily Labeled Data
Yingbin Bai Tongliang Liu*
Trustworthy Machine Learning Lab, University of Sydney
Abstract tistically consistent or inconsistent classifiers. Methods in
the first category intent to design classifier-consistent algo-
Examples that are close to the decision boundary—that rithms [58, 14, 3 ...
京公网安备 11010802022788号
