• Home
  • Search
  • Semi-Supervised Learning via Triplet Network Based Active Learning (Student Abstract)
  • https://doi.org/10.1609/aaai.v35i18.17948Copy DOI Icon

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

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

In recent years, deep learning models have pushed state-of-the-art accuracies for several machine learning tasks. However, such models require a large amount of (supervised) data for training. While unlabelled data is available in abundance, manually labeling them is very costly. Active learning techniques helps in utilizing unlabelled data which may result in an improved classification model. In this research, we present an active learning algorithm which can help in increasing performance of deep learning models by using large amount of unlabelled data. A novel active learning algorithm, Triplet AL is proposed which uses a triplet network to select samples from an unlabelled data set. Previous active learning methods rely on classification model's final prediction scores as a measure of confidence for an unlabelled sample. We propose a more reliable confidence measure, termed as Top-Two-Margin which is given by the Triplet Network. The proposed algorithm shows improved performance compared to other active learning approaches.

Similar Papers
  • Research Article
  • Citations34

Efficient Active Learning by Querying Discriminative and Representative Samples and Fully Exploiting Unlabeled Data.

  • Aug 26, 2020
  • IEEE Transactions on Neural Networks and Learning Systems
  • Bin Gu +3
  • PDF
  • Research Article
  • Citations29

Active semi-supervised learning for biological data classification

  • Aug 19, 2020
  • PLoS ONE
  • Guilherme Camargo +2
  • 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
  • Conference Article
  • Citations1

An AUC-based Active Learning Algorithm via LogitBoost for Binary Classification

  • Jul 01, 2018
  • Zhe-Bin Zhang +1
  • Research Article
  • Citations42

Particle Swarm Optimization Based Swarm Intelligence for Active Learning Improvement: Application on Medical Data Classification

  • Aug 05, 2020
  • Cognitive Computation
  • Nawel Zemmal +6
  • 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
  • Citations12

Semi-Supervised Learning

  • Jan 01, 2009
  • Tobias Scheffer
  • Research Article
  • Citations3

Quantum speedup for pool-based active learning

  • Sep 30, 2019
  • Quantum Information Processing
  • Zhimin He +4
  • Conference Article
  • Citations35

Active Learning from Positive and Unlabeled Data

  • Dec 01, 2011
  • Alireza Ghasemi +4
  • Dissertation

Active and Multi-View Machine Learning for microRNA Prediction

  • Jan 01, 2018
  • Mohsen Sheikh Hassani
  • Research Article
  • Citations82

Active Batch Selection via Convex Relaxations with Guaranteed Solution Bounds.

  • Oct 01, 2015
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • Shayok Chakraborty +4
  • Conference Article
  • Citations8

Learning Rare Category Classifiers on a Tight Labeling Budget

  • Oct 01, 2021
  • Ravi Teja Mullapudi +4
  • Conference Article
  • Citations6

Design and analysis of the WCCI 2010 active learning challenge

  • Jul 01, 2010
  • Isabelle Guyon +3
  • Conference Article
  • Citations4

Deep Active Transfer Learning for Image Recognition

  • Jul 01, 2020
  • Ankita Singh +1
  • Research Article
  • Citations31

How useful is active learning for image‐based plant phenotyping?

  • Jan 01, 2021
  • The Plant Phenome Journal
  • Koushik Nagasubramanian +7
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.