• Home
  • Search
  • A Two-Stage Active Learning Method for Image Classification
  • https://doi.org/10.1109/iciea54703.2022.10005962Copy DOI Icon

A Two-Stage Active Learning Method for Image Classification

  • Dec 16, 2022
  • Feiyue Wang +4 more
Show More
  • Abstract
  • Literature Map
  • References
  • Similar Papers
Abstract

Recent successes in learning-based image classification rely heavily on a large number of annotated training samples, which often require considerable human effort. In this paper, we propose a new two-stage active learning (AL) method for image classification with a query strategy considering both uncertainty and diversity. In the first stage, the uncertainty is used to determine the candidate set. In the second stage, the candidate set is clustered, and the nearest sample from the cluster center is selected to increase the diversity of samples. Our method uses Poly-1 loss as the classification loss and Binary Cross Entropy (BCE) as the binary loss to distinguish between the labeled samples and the unlabeled samples. We train the two classifiers in a joint way and evaluate our method on the CIFAR10 and CIFAR100 datasets. The rich experimental results show that the proposed method outperforms the state-of-the-art AL methods in image classification tasks.

Similar Papers
  • Book Chapter
  • Citations6

Image Classification Using Graph-Based Representations and Graph Neural Networks

  • Jan 01, 2021
  • Giannis Nikolentzos +3
  • Research Article

Principal Component Analysis on Convolutional Neural Network Using Transfer Learning Method for Image Classification of Cifar-10 Dataset

  • Dec 25, 2024
  • Register: Jurnal Ilmiah Teknologi Sistem Informasi
  • M Al Haris +2
  • Research Article
  • Citations19

Semi-Supervised Image Classification Based on Local and Global Regression

  • Oct 01, 2015
  • IEEE Signal Processing Letters
  • Mingbo Zhao +3
  • Conference Article

Integrating multiple information of active learning for image classification

  • Dec 01, 2013
  • Haihui Xu +4
  • 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
  • Conference Article

Angular joint loss for image classification

  • Jun 30, 2021
  • Hao Ai +1
  • Research Article
  • Citations6

Balanced Active Learning Method for Image Classification

  • Jan 01, 2017
  • Acta Cybernetica
  • Dávid Papp +1
  • Research Article

Image Classification Using Deep Learning: A Systematic Review

  • Dec 24, 2025
  • Neutrosophic Optimization and Intelligent Systems
  • Maher Khalaf Hussein +2
  • Dissertation

On interpretation methods for deep neural networks

  • Jan 01, 2023
  • Mohammed Ismael Khaleel
  • Research Article
  • Citations5

Convex hull-based distance metric learning for image classification

  • Apr 17, 2021
  • Computational and Applied Mathematics
  • Xue Zhang +2
  • Research Article
  • Citations622

Class-Incremental Learning: Survey and Performance Evaluation on Image Classification.

  • May 01, 2023
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • Marc Masana +5
  • Research Article
  • Citations10

Variable-length deep convolutional neural networks by Internet Protocol Addresses Whale Optimization Algorithm for random and complex image classification

  • Jan 10, 2023
  • Waves in Random and Complex Media
  • Mohammad Khishe
  • Research Article
  • Citations47

Abnormality Detection in Musculoskeletal Radiographs Using Capsule Network

  • Jan 01, 2019
  • IEEE Access
  • A F M Saif +3
  • Research Article
  • Citations31

Patch-level Tumor Classification in Digital Histopathology Images with Domain Adapted Deep Learning.

  • Jul 01, 2018
  • Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference
  • Tian Xia +3
  • Book Chapter
  • Citations1

Evaluation of Machine Learning Methods for Image Classification: A Case Study of Facility Surface Damage

  • Jan 01, 2022
  • Ching-Lung Fan
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.