ST-LP: self-training and label propagation for semi-supervised classification

Due to the particularly high costs of manual data labeling, especially in the field of medical imaging, and the necessity for specialized knowledge, there is a growing interest in semi-supervised methods. In this paper, a novel framework of Self-Training with Label Propagation (ST-LP) is proposed fo...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Multimedia tools and applications Jg. 83; H. 41; S. 89335 - 89353
Hauptverfasser: Lin, Chih-Wen, Chiang, Chen-Kuo, Wang, Yu-An, Yang, Yue-Lin, Li, Hao-Ting, Lin, Tzu-Chieh
Format: Journal Article
Sprache:Englisch
Veröffentlicht: New York Springer US 01.12.2024
Springer Nature B.V
Schlagworte:
1237: Advanced Deep Learning for Computer Vision and Multimedia Applications
Classification
Computer Communication Networks
Computer Science
Data Structures and Information Theory
Datasets
Labeling
Labels
Medical imaging
Multimedia Information Systems
Propagation
Special Purpose and Application-Based Systems
Self-training
Label propagation
Semi-supervised learning
Image classification
ISSN:1573-7721, 1380-7501, 1573-7721
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Due to the particularly high costs of manual data labeling, especially in the field of medical imaging, and the necessity for specialized knowledge, there is a growing interest in semi-supervised methods. In this paper, a novel framework of Self-Training with Label Propagation (ST-LP) is proposed for semi-supervised classification. It integrates self-training and label propagation to address the challenge of limited labeled data in classification tasks, a concern exacerbated by the especially expensive nature of data labeling in the medical domain. Our method involves leveraging two soft pseudo-labels generated from a pre-training fine-tuned model and label propagation scheme as inputs for a pseudo-label prediction module. Subsequently, confident predictions from this model are selected as pseudo-labeled data. The effectiveness of our approach is demonstrated through experiments conducted on diverse datasets, including the MNIST dataset and two medical classification datasets: ISIC2018 and MURA. Experimental results demonstrate that our method consistently achieved comparable or outstanding results when dealing with large amounts of unlabeled data.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1573-7721
1380-7501
1573-7721
DOI:10.1007/s11042-024-20341-5