• Home
  • Search
  • Toward Label-Efficient Neural Network Training: Diversity-Based Sampling in Semi-Supervised Active Learning
  • Cite Icon7
  • https://doi.org/10.1109/access.2023.3236529Copy DOI Icon

Toward Label-Efficient Neural Network Training: Diversity-Based Sampling in Semi-Supervised Active Learning

Show More
  • Abstract
  • Highlights & Summary
  • PDF
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Collecting large-labeled data is an expensive and challenging issue for training deep neural networks. To address this issue, active learning is recently studied where the active learner provides informative samples for labeling. Diversity-based sampling algorithms are commonly used for representation-based active learning. In this paper, a new diversity-based sampling is introduced for semi-supervised active learning. To select more informative data at the initial stage, we devise a diversity-based initial dataset selection method by using self-supervised representation. We further propose a new active learning query strategy, which exploits both consistency and diversity. Comparative experiments show that the proposed method can outperform other active learning approaches on two public datasets.

Loading PDF

Similar Papers
  • PDF
  • Research Article
  • Citations29

Active semi-supervised learning for biological data classification

  • Aug 19, 2020
  • PLoS ONE
  • Guilherme Camargo +2
  • Research Article

Consistency-based Semi-supervised Evidential Active Learning Framework for Robust Classification of Radiology Images.

  • May 25, 2026
  • IEEE journal of biomedical and health informatics
  • Shafa Balaram +13
  • Conference Article
  • Citations9

Exploiting Diversity of Unlabeled Data for Label-Efficient Semi-Supervised Active Learning

  • Aug 21, 2022
  • Felix Buchert +2
  • Research Article
  • Citations11

A two-phase hybrid of semi-supervised and active learning approach for sequence labeling

  • Apr 17, 2013
  • Intelligent Data Analysis
  • Hamed Hassanzadeh +1
  • Conference Article
  • Citations5

ActiveMatch: End-To-End Semi-Supervised Active Representation Learning

  • Oct 16, 2022
  • Xinkai Yuan +2
  • Research Article
  • Citations43

A novel myocardial infarction localization method using multi-branch DenseNet and spatial matching-based active semi-supervised learning

  • May 25, 2022
  • Information Sciences
  • Ziyang He +7
  • Book Chapter

Semi-supervised Dictionary Active Learning for Pattern Classification

  • Jan 01, 2018
  • Qin Zhong +2
  • Research Article
  • Citations30

SEAL: Semisupervised Adversarial Active Learning on Attributed Graphs.

  • Aug 04, 2020
  • IEEE Transactions on Neural Networks and Learning Systems
  • Yayong Li +2
  • Conference Article
  • Citations14

Network Intrusion Detection Based on Active Semi-supervised Learning

  • Jun 01, 2021
  • Yong Zhang +4
  • Research Article
  • Citations9

A Disk Failure Prediction Method Based on Active Semi-supervised Learning

  • Nov 12, 2022
  • ACM Transactions on Storage
  • Yang Zhou +2
  • Conference Article
  • Citations1

Active Learning with Spatial Distribution based Semi-Supervised Extreme Learning Machine for Multiclass Classification

  • May 01, 2019
  • Yuefan Xu +2
  • Conference Article
  • Citations3

Transient Stability Assessment of Power Systems Based on Semi-Supervised Active Learning

  • Mar 23, 2023
  • Yuanzhuo Sheng +3
  • Research Article
  • Citations30

Semi-supervised active transfer learning for fetal ECG arrhythmia detection

  • Jan 01, 2023
  • Computer Methods and Programs in Biomedicine Update
  • Mohammad Reza Mohebbian +2
  • Dissertation

Semi-supervised and Active Learning Models for Software Fault Prediction

  • Jan 01, 2015
  • Huihua Lu
  • Research Article
  • Citations37

Combining committee-based semi-supervised learning and active learning

  • Jul 11, 2010
  • Journal of Computer Science and Technology
  • Mohamed Farouk Abdel Hady +1
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.