• Home
  • Search
  • Similarity-Based Active Learning for Image Classification Under Class Imbalance
  • Cite Icon31
  • https://doi.org/10.1109/icdm.2018.00196Copy DOI Icon

Similarity-Based Active Learning for Image Classification Under Class Imbalance

  • Nov 1, 2018
  • Chuanhai Zhang +5 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Many image classification tasks (e.g., medical image classification) have a severe class imbalance problem. Convolutional neural network (CNN) is currently a state-of-the-art method for image classification. CNN relies on a large training dataset to achieve high classification performance. However, manual labeling is costly and may not even be feasible for medical domain. In this paper, we propose a novel similarity-based active deep learning framework (SAL) that deals with class imbalance. SAL actively learns a similarity model to recommend unlabeled rare class samples for experts' manual labeling. Based on similarity ranking, SAL recommends high confidence unlabeled common class samples for automatic pseudo-labeling without experts' labeling effort. To the best of our knowledge, SAL is the first active deep learning framework that deals with a significant class imbalance. Our experiments show that SAL consistently outperforms two other recent active deep learning methods on two challenging datasets. What's more, SAL obtains nearly the upper bound classification performance (using all the images in the training dataset) while the domain experts labeled only 5.6% and 7.5% of all images in the Endoscopy dataset and the Caltech-256 dataset, respectively. SAL significantly reduces the experts' manual labeling efforts while achieving near optimal classification performance.

Similar Papers
  • Research Article
  • Citations3

VisActive: Visual-concept-based Active Learning for Image Classification under Class Imbalance

  • Nov 10, 2023
  • ACM Transactions on Multimedia Computing, Communications, and Applications
  • Mohammed Khaleel +5
  • Research Article
  • Citations17

Dirichlet Process Based Active Learning and Discovery of Unknown Classes for Hyperspectral Image Classification

  • Aug 01, 2016
  • IEEE Transactions on Geoscience and Remote Sensing
  • Hao Wu +1
  • Conference Article
  • Citations13

Active Learning for Image Classification: A Deep Reinforcement Learning Approach

  • Sep 01, 2019
  • Le Sun +1
  • Conference Article
  • Citations6

Multi-label active learning for image classification with asymmetrical conditional dependence

  • Jul 01, 2016
  • Jian Wu +4
  • Conference Article
  • Citations7

Semi-supervised active learning image classification method based on Tri-Training algorithm

  • Mar 01, 2020
  • Yongjun Zhang +1
  • Research Article
  • Citations5

Active Learning with Pre-trained Language Models for Named Entity Recognition in Requirements Engineering

  • Jan 01, 2024
  • Procedia CIRP
  • M Riesener +6
  • Conference Article
  • Citations10

Weak Labeled Multi-Label Active Learning for Image Classification

  • Oct 13, 2015
  • Shiquan Zhao +5
  • Research Article
  • Citations50

Class-wise Graph Embedding-Based Active Learning for Hyperspectral Image Classification

  • Jan 01, 2023
  • IEEE Transactions on Geoscience and Remote Sensing
  • Xiaolong Liao +3
  • 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
  • Citations199

Efficient Active Learning for Image Classification and Segmentation Using a Sample Selection and Conditional Generative Adversarial Network

  • Jan 01, 2018
  • Dwarikanath Mahapatra +3
  • Conference Article
  • Citations26

Non-uniform Subset Selection for Active Learning in Structured Data

  • Jul 01, 2017
  • Sujoy Paul +2
  • Research Article

Data-efficient learning for accurate identification of MAPK1 inhibitors using an active meta-deep learning framework.

  • Feb 03, 2026
  • Journal of cheminformatics
  • Darlene Nabila Zetta +1
  • PDF
  • Research Article
  • Citations30

Unlabeled data selection for active learning in image classification

  • Jan 03, 2024
  • Scientific Reports
  • Xiongquan Li +5
  • Conference Article

A Two-Stage Active Learning Method for Image Classification

  • Dec 16, 2022
  • Feiyue Wang +4
  • Research Article
  • Citations1

Active Stacking-Deep Learning with Strategic Samplingfor Small and Imbalanced Chemical Toxicity Prediction

  • Nov 04, 2025
  • ACS Omega
  • Darlene Nabila Zetta +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.