• Home
  • Search
  • Deep Active Learning for Computer Vision Tasks: Methodologies, Applications, and Challenges
  • Cite Icon47
  • https://doi.org/10.3390/app12168103Copy DOI Icon

Deep Active Learning for Computer Vision Tasks: Methodologies, Applications, and Challenges

Show More
  • Abstract
  • PDF
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Active learning is a label-efficient machine learning method that actively selects the most valuable unlabeled samples to annotate. Active learning focuses on achieving the best possible performance while using as few, high-quality sample annotations as possible. Recently, active learning achieved promotion combined with deep learning-based methods, which are named deep active learning methods in this paper. Deep active learning plays a crucial role in computer vision tasks, especially in label-insensitive scenarios, such as hard-to-label tasks (medical images analysis) and time-consuming tasks (autonomous driving). However, deep active learning still has some challenges, such as unstable performance and dirty data, which are future research trends. Compared with other reviews on deep active learning, our work introduced the deep active learning from computer vision-related methodologies and corresponding applications. The expected audience of this vision-friendly survey are researchers who are working in computer vision but willing to utilize deep active learning methods to solve vision problems. Specifically, this review systematically focuses on the details of methods, applications, and challenges in vision tasks, and we also introduce the classic theories, strategies, and scenarios of active learning in brief.

Loading PDF

Similar Papers
  • Research Article
  • Citations24

Deep Bayesian Active Learning for Learning to Rank: A Case Study in Answer Selection

  • Nov 01, 2022
  • IEEE Transactions on Knowledge and Data Engineering
  • Qunbo Wang +3
  • Research Article
  • Citations110

A comprehensive survey on deep active learning in medical image analysis

  • May 13, 2024
  • Medical image analysis
  • Haoran Wang +5
  • Research Article
  • Citations14

A Chinese power text classification algorithm based on deep active learning

  • Nov 22, 2023
  • Applied Soft Computing
  • Song Deng +6
  • Book Chapter
  • Citations4

New Leadership Education and Deep Active Learning

  • Sep 13, 2017
  • Mikinari Higano
  • Research Article
  • Citations175

A Survey on Active Deep Learning: From Model Driven to Data Driven

  • Jan 31, 2022
  • ACM Computing Surveys
  • Peng Liu +4
  • Book Chapter
  • Citations4

Deep Active Self-paced Learning for Biomedical Image Analysis

  • Nov 19, 2019
  • Wenzhe Wang +9
  • Research Article
  • Citations1

Label shift conditioned hybrid querying for deep active learning

  • May 18, 2023
  • Knowledge-Based Systems
  • Jiaqi Li +7
  • Conference Article
  • Citations2

Feature Dimensionality Reduction with Variational Autoencoders in Deep Bayesian Active Learning

  • Jun 09, 2021
  • Pınar Ezgi Çöl +1
  • Conference Article
  • Citations580

Deep Bayesian active learning with image data

  • Nov 27, 2017
  • Apollo (University of Cambridge)
  • Yarin Gal +2
  • Book Chapter
  • Citations29

Breast Cancer Histopathological Image Classification via Deep Active Learning and Confidence Boosting

  • Jan 01, 2018
  • Baolin Du +4
  • Book Chapter
  • Citations2

Scalable Batch Acquisition for Deep Bayesian Active Learning

  • Jan 01, 2023
  • Aleksandr Rubashevskii +2
  • Research Article
  • Citations3

Detection of white blood cells in microscopic leucorrhea images based on deep active learning

  • Mar 17, 2020
  • Sheng wu yi xue gong cheng xue za zhi = Journal of biomedical engineering = Shengwu yixue gongchengxue zazhi
  • Mengxi Ju +2
  • Conference Article
  • Citations20

Deep Active Learning for Text Classification

  • Aug 27, 2018
  • Bang An +2
  • PDF
  • Research Article
  • Citations6

A Weakly Supervised Method for Mud Detection in Ores Based on Deep Active Learning

  • May 30, 2020
  • Mathematical Problems in Engineering
  • Zhijian Huang +3
  • Dissertation

Active Uncertainty Representation Learning: Toward More Label Efficiency in Deep Learning

  • Jan 01, 2024
  • Salman Mohamadi
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.