• Home
  • Search
  • Semi-Supervised and Unsupervised Deep Visual Learning: A Survey.
  • Open Access IconOpen Access
  • Cite Icon188
  • https://doi.org/10.1109/tpami.2022.3201576Copy DOI Icon

Semi-Supervised and Unsupervised Deep Visual Learning: A Survey.

  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

State-of-the-art deep learning models are often trained with a large amount of costly labeled training data. However, requiring exhaustive manual annotations may degrade the model's generalizability in the limited-label regime.Semi-supervised learning and unsupervised learning offer promising paradigms to learn from an abundance of unlabeled visual data. Recent progress in these paradigms has indicated the strong benefits of leveraging unlabeled data to improve model generalization and provide better model initialization. In this survey, we review the recent advanced deep learning algorithms on semi-supervised learning (SSL) and unsupervised learning (UL) for visual recognition from a unified perspective. To offer a holistic understanding of the state-of-the-art in these areas, we propose a unified taxonomy. We categorize existing representative SSL and UL with comprehensive and insightful analysis to highlight their design rationales in different learning scenarios and applications in different computer vision tasks. Lastly, we discuss the emerging trends and open challenges in SSL and UL to shed light on future critical research directions.

Similar Papers
  • Research Article
  • Citations22

Discriminative semi-supervised learning via deep and dictionary representation for image classification

  • Mar 17, 2023
  • Pattern Recognition
  • Meng Yang +4
  • Research Article
  • Citations39

Unsupervised and semi-supervised extreme learning machine with wavelet kernel for high dimensional data

  • Jun 22, 2016
  • Memetic Computing
  • Nan Zhang +1
  • Research Article
  • Citations1

Detecting Fraud in Automated Teller Machine Transactions in the Nigerian Bank System Using Unsupervised Deep Learning

  • Jan 01, 2024
  • Advances in Multidisciplinary & Scientific Research Journal Publication
  • Hakeem Olusegun Ojulari +2
  • Research Article
  • Citations15

Semi-Supervised Temporal Meta-Learning Framework for Wind Turbine Bearing Fault Diagnosis Under Limited Annotation Data

  • Jan 01, 2024
  • IEEE Transactions on Instrumentation and Measurement
  • Hao Su +3
  • Conference Article
  • Citations6

Dual-Leak: Deep Unsupervised Active Learning for Cross-Device Profiled Side-Channel Leakage Analysis

  • May 01, 2023
  • Honggang Yu +6
  • Conference Article
  • Citations13

Pseudo-Labeling Using Gaussian Process for Semi-Supervised Deep Learning

  • Jan 01, 2018
  • Zhun Li +2
  • Research Article
  • Citations1

Review of optimization methods for supervised deep learning

  • Jan 01, 2023
  • Journal of Image and Graphics
  • Jiang Lingyi +4
  • PDF
  • Research Article
  • Citations72

Unsupervised deep learning reveals prognostically relevant subtypes of glioblastoma

  • Oct 01, 2017
  • BMC Bioinformatics
  • Jonathan D Young +2
  • Research Article
  • Citations2

Automatic Discovery of Railway Train Driving Modes Using Unsupervised Deep Learning

  • Jun 27, 2019
  • ISPRS International Journal of Geo-Information
  • Han Zheng +2
  • Research Article
  • Citations19

A real use case of semi-supervised learning for mammogram classification in a local clinic of Costa Rica

  • Jan 01, 2022
  • Medical & Biological Engineering & Computing
  • Saul Calderon-Ramirez +6
  • Conference Article
  • Citations1

A semi-supervised deep learning method in network intrusion detection

  • Jun 01, 2023
  • Zhanbo Li +1
  • Conference Article
  • Citations4

MUSCLE: Strengthening Semi-Supervised Learning Via Concurrent Unsupervised Learning Using Mutual Information Maximization

  • Jan 01, 2021
  • Hanchen Xie +3
  • Research Article

Abstract 184: The utility of deep metric learning for breast cancer identification on mammographic images

  • Jul 01, 2021
  • Cancer Research
  • Justin Du +8
  • Research Article

Edge-Optimized Semi-Supervised Deep Learning for Power Line Component Inspection.

  • Jun 23, 2026
  • Sensors (Basel, Switzerland)
  • Nico Surantha +2
  • Book Chapter
  • Citations8

Semi-supervised Deep Learning for Network Anomaly Detection

  • Jan 01, 2020
  • Yuanyuan Sun +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.