.png){kind=icon}
.png){kind=icon}
Return
A Re-node Self-training Approach for Deep Graph-based Semi-supervised Classification on Multi-view Image Data
.png){kind=icon}
OA
AI
DOI：10.1016/j.inffus.2025.103887.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• We deal with deep graph-based semi-supervised classification for multi-view image data • A scheme for unified graph estimation for multi-view and non-graph data is proposed • We introduce a dynamic pseudo-labeling loss function based on soft confidence • The labeled samples are weighted based on the graph topology imbalance • Performance is evaluated on five public multi-view image datasets
Keywords:
Self-taught
Multi-view data
Semi-supervised classification
Pseudo-label
Graph construction
Graph fusion
Graph Convolutional Networks
Topological imbalance
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
15.5
Papers:
4.1K
Citations:
2.7W