CoVar: Confidence-Variance-Guided Pseudo-Label Selection for Semi-Supervised Learning 文章

ArXiv CS.AI2026-06-11NEWSen作者: Jinshi Liu, Lei He, Pan Liu

详细信息

来源站点
ArXiv CS.AI
作者
Jinshi Liu, Lei He, Pan Liu
文章类型
NEWS
语言
en
发布日期
2026-06-11

摘要

arXiv:2601.11670v3 Announce Type: replace-cross Abstract: Pseudo-label selection in semi-supervised learning is commonly driven by maximum-confidence thresholds, yet confidence alone can be unreliable under model overconfidence and class imbalance. We propose CoVar, a confidence--variance framework that assesses pseudo-label reliability by jointly modeling Maximum Confidence (MC) and Residual-Class Variance (RCV). Starting from entropy minimization, we derive a second-order cross-entropy approximation showing that low-loss pseudo-labels are favored when MC is high and RCV is low, with a confidence-dependent penalty that becomes stronger for near-certain predictions. Based on this criterion, CoVar embeds predictions into a two-dimensional confidence--variance space and uses SVD-based spectral relaxation to separate reliable and unreliable predictions without hand-tuned confidence thresholds. Cluster-wise Gaussian weighting then converts this separation into per-sample training weights.

相关事件

暂无数据

相关公司

暂无数据

相关人物

暂无数据

相关产品

暂无数据