AIBullisharXiv – CS AI · Feb 277/108
🧠
A Confidence-Variance Theory for Pseudo-Label Selection in Semi-Supervised Learning
Researchers introduce a Confidence-Variance (CoVar) theory framework that improves pseudo-label selection in semi-supervised learning by combining maximum confidence with residual-class variance. The method addresses overconfidence issues in deep networks and demonstrates consistent improvements across multiple datasets including PASCAL VOC, Cityscapes, CIFAR-10, and Mini-ImageNet.
$NEAR