• Home
  • Search
  • Deep Bayesian Active Semi-Supervised Learning
  • Cite Icon25
  • https://doi.org/10.1109/icmla.2018.00031Copy DOI Icon

Deep Bayesian Active Semi-Supervised Learning

  • Dec 1, 2018
  • Matthias Rottmann +2 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

In many applications the process of generating label information is expensive and time consuming. We present a new method that combines active and semi-supervised deep learning to achieve high generalization performance from a deep convolutional neural network with as few known labels as possible. In a setting where a small amount of labeled data as well as a large amount of unlabeled data is available, our method first learns the labeled data set. This initialization is followed by an expectation maximization algorithm, where further training reduces classification entropy on the unlabeled data by targeting a low entropy fit which is consistent with the labeled data. In addition the algorithm asks at a specified frequency an oracle for labels of data with entropy above a certain entropy quantile. Using this active learning component we obtain an agile labeling process that achieves high accuracy, but requires only a small amount of known labels. For the MNIST dataset we report an error rate of 2.06% using only 300 labels and 1.06% for 1,000 labels. These results are obtained without employing any special network architecture or data augmentation.

Similar Papers
  • Conference Article
  • Citations4

Deep Active Transfer Learning for Image Recognition

  • Jul 01, 2020
  • Ankita Singh +1
  • Conference Article
  • Citations580

Deep Bayesian active learning with image data

  • Nov 27, 2017
  • Apollo (University of Cambridge)
  • Yarin Gal +2
  • Conference Article
  • Citations4

Deep Active Learning with Relative Label Feedback: An Application to Facial Age Estimation

  • Jul 18, 2021
  • Ankita Singh +1
  • Research Article
  • Citations14

A unified deep semi-supervised graph learning scheme based on nodes re-weighting and manifold regularization

  • Nov 19, 2022
  • Neural Networks
  • Fadi Dornaika +2
  • Research Article

Semi-Supervised Learning via Triplet Network Based Active Learning (Student Abstract)

  • May 18, 2021
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Divyanshu Sundriyal +3
  • Conference Article
  • Citations3

Deep Active Learning with Range Feedback for Facial Age Estimation

  • Jul 18, 2022
  • Aditya R Bhattacharya +1
  • Research Article
  • Citations40

A Novel Two-Stage Unsupervised Fault Recognition Framework Combining Feature Extraction and Fuzzy Clustering for Collaborative AIoT

  • Apr 29, 2021
  • IEEE Transactions on Industrial Informatics
  • Xufeng Hu +3
  • Book Chapter
  • Citations16

Deep Active Learning for Image Regression

  • Jan 01, 2020
  • Hiranmayi Ranganathan +3
  • Research Article
  • Citations69

PARSE: Pairwise Alignment of Representations in Semi-Supervised EEG Learning for Emotion Recognition

  • Oct 01, 2022
  • IEEE Transactions on Affective Computing
  • Guangyi Zhang +2
  • PDF
  • Research Article
  • Citations29

Active semi-supervised learning for biological data classification

  • Aug 19, 2020
  • PLoS ONE
  • Guilherme Camargo +2
  • Book Chapter
  • Citations1

Malware Classification Based on Semi-Supervised Learning

  • Jan 01, 2022
  • Yu Ding +8
  • Research Article
  • Citations75

Batch Mode Active Sampling Based on Marginal Probability Distribution Matching

  • Sep 01, 2013
  • ACM Transactions on Knowledge Discovery from Data
  • Rita Chattopadhyay +5
  • 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
  • Citations1

A review of research and development of semi-supervised learning strategies for medical image processing

  • Jan 16, 2024
  • EAI Endorsed Transactions on e-Learning
  • Shengke Yang
  • Research Article
  • Citations47

Matrix Completion for Graph-Based Deep Semi-Supervised Learning

  • Jul 17, 2019
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Fariborz Taherkhani +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.