Self-taught graph-based semi-supervised learning for multi-view image data

doi:10.1016/j.patcog.2026.114731

Self-taught graph-based semi-supervised learning for multi-view image data

2026-09-03

0

OA

AI

DOI：10.1016/j.patcog.2026.114731

Original

Original request for help

Save

Abstract

En 中文

• Integrate pseudo-labeling with graph-based techniques for multi-view image data. • Alleviate concerns regarding the establishment of threshold values. • Ensure that potentially valuable pseudo-label information is not overlooked. • Mitigate the impact of inaccurate predictions during the early training stages. • Experiments are performed on six public multi-view image datasets.

Keywords:

Semi-supervised classification

Self-taught

Multi-view data

Pseudo-label

Graph learning

Fused graph

Graph convolutional networks

Self-taught graph-based semi-supervised learning for multi-view image data

Abstract

Journal

Organization

Cited Papers