Semi-Supervised Regression via Hierarchical Confidence Screening and Neighbor-Guided Pseudo-Label Calibration

Semi-supervised regression enhances model performance by effectively utilizing unlabeled data during training. Most existing methods select only a small subset of high-confidence unlabeled samples based on single confidence metrics to participate in model training. However, these approaches suffer f...

Popoln opis

Bibliografske podrobnosti

Principais autores:	Yunfei Mao, Bowen Yao
Format:	Artigo
Jezik:	Inglês
Izdano:	IEEE 2026-01-01
Serija:	IEEE Access
Teme:	Confidence hierarchical confidence screening neighbor-guided pseudo-label calibration safe labeling technique semi-supervised regression
Online dostop:	https://ieeexplore.ieee.org/document/11474475/
Oznake:	Označite Brez oznak, prvi označite!