• Home
  • Search
  • Joint-AL: Joint Discriminative and Generative Active Learning for Cross-Domain Semantic Concept Classification
  • Cite Icon1
  • https://doi.org/10.1109/icsc.2010.86Copy DOI Icon

Joint-AL: Joint Discriminative and Generative Active Learning for Cross-Domain Semantic Concept Classification

  • Sep 1, 2010
  • Huan Li +4 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

As multimedia data come from a wide variety of domains, each having its distinctive data distributions, cross-domain video semantic concept classification becomes an important task in semantic computing. Its challenge arises from the different distribution (in feature space) of the concept between the source and the target domain, which makes a classifier trained on a source domain perform poorly on a target domain. Active learning can be employed to reuse the existing classifier in order to avoid expensively labeling target domain data for building a new classifier, which queries the labels for a number of most ambiguous samples in target domain and uses these samples to refine the source domain classifier. This discriminative query strategy, used by many traditional active learning methods, could fail if the difference in the feature space distribution of the concept is too large. A generative query strategy is proposed by us in this paper, to deal with large differences between two domains of one semantic concept, which queries samples that are most unlikely to be generated from current distribution. We then present a joint active learning method by adaptively combining the dis-criminative and the generative query strategies. This method dynamically adapts to the distribution differences and results a hybrid strategy that performs more robustly compared to either single strategy. We evaluate the proposed approaches in cross-domain semantic classification based on TRECVID corpora. The results show the effectiveness of our joint method.

Similar Papers
  • Research Article
  • Citations9

Active Multiple Kernel Fredholm Learning for Hyperspectral Images Classification

  • Feb 12, 2020
  • IEEE Geoscience and Remote Sensing Letters
  • Arash Saboori +2
  • Research Article
  • Citations16

Cross-domain video concept detection: A joint discriminative and generative active learning approach

  • May 16, 2012
  • Expert Systems with Applications
  • Huan Li +4
  • Research Article
  • Citations4

Enhancing Cross-Domain Remote Sensing Scene Classification by Multi-Source Subdomain Distribution Alignment Network

  • Apr 05, 2025
  • Remote Sensing
  • Yong Wang +6
  • PDF
  • Research Article

Learning Transferable Convolutional Proxy by SMI-Based Matching Technique

  • Oct 14, 2020
  • Shock and Vibration
  • Wei Jin +1
  • Research Article
  • Citations6

Cross-Domain Urban Land Use Classification via Scenewise Unsupervised Multisource Domain Adaptation With Transformer

  • Jan 01, 2024
  • IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
  • Mengmeng Li +3
  • Research Article
  • Citations4

Transfer learning method for specific emitter identification based on pseudo‐labelling and meta‐learning

  • May 17, 2024
  • IET Radar, Sonar & Navigation
  • Qing Ling +4
  • Research Article
  • Citations68

Bridging Domains Using World Wide Knowledge for Transfer Learning

  • Jun 01, 2010
  • IEEE Transactions on Knowledge and Data Engineering
  • Evan Wei Xiang +3
  • Research Article

Adversarial Unsupervised Domain Adaptation Image Classification Method Based on Contrastive Learning

  • May 01, 2025
  • Journal of Computer-Aided Design & Computer Graphics
  • Ting Wang +3
  • Research Article
  • Citations2

Heterogeneous domain adaptation by Features Normalization and Data Topology Preserving

  • Jul 29, 2022
  • Knowledge-Based Systems
  • Mohammad Amin Pirbonyeh +3
  • Research Article

Multi-category Classification Problem Oriented Subsampling-Based Active Learning Method

  • Sep 01, 2020
  • Journal of Physics: Conference Series
  • Wei Shi +4
  • Conference Article
  • Citations22

DASA: Domain adaptation in stacked autoencoders using systematic dropout

  • Nov 01, 2015
  • Abhijit Guha Roy +1
  • Conference Article
  • Citations23

Unsupervised transfer learning via Low-Rank Coding for image clustering

  • Jul 01, 2016
  • Sheng Li +1
  • Conference Article
  • Citations2

Cross-Domain Sentiment Classification with Attention-Assisted GAN

  • Dec 01, 2021
  • Yi-Fan Li +3
  • Research Article
  • Citations12

Active Learning with Cross-Class Similarity Transfer

  • Feb 12, 2017
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Yuchen Guo +3
  • Research Article
  • Citations6

OHetTLAL: An Online Transfer Learning Method for Fingerprint-Based Indoor Positioning.

  • Nov 22, 2022
  • Sensors
  • Hailu Tesfay Gidey +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.