• Home
  • Search
  • Imbalanced Open Set Domain Adaptation via Moving-Threshold Estimation and Gradual Alignment
  • Open Access IconOpen Access
  • Cite Icon26
  • https://doi.org/10.1109/tmm.2023.3297768Copy DOI Icon

Imbalanced Open Set Domain Adaptation via Moving-Threshold Estimation and Gradual Alignment

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

Multimedia applications are often associated with cross-domain knowledge transfer, where Unsupervised Domain Adaptation (UDA) can be used to reduce the domain shifts. Open Set Domain Adaptation (OSDA) aims to transfer knowledge from a well-labeled source domain to an unlabeled target domain under the assumption that the target domain contains unknown classes. Existing OSDA methods consistently lay stress on the covariate shift, ignoring the potential label shift problem. The performance of OSDA methods degrades drastically under intra-domain class imbalance and inter-domain label shift. However, little attention has been paid to this issue in the community. In this paper, the Imbalanced Open Set Domain Adaptation (IOSDA) is explored where the covariate shift, label shift and category mismatch exist simultaneously. To alleviate the negative effects raised by label shift in OSDA, we propose Open-set Moving-threshold Estimation and Gradual Alignment (OMEGA) - a novel architecture that improves existing OSDA methods on class-imbalanced data. Specifically, a novel unknown-aware target clustering scheme is proposed to form tight clusters in the target domain to reduce the negative effects of label shift and intra-domain class imbalance. Furthermore, moving-threshold estimation is designed to generate specific thresholds for each target sample rather than using one for all. Extensive experiments on IOSDA, OSDA and OPDA benchmarks demonstrate that our method could significantly outperform existing state-of-the-arts.

Similar Papers
  • Research Article
  • Citations202

Open Set Domain Adaptation: Theoretical Bound and Algorithm.

  • Sep 03, 2020
  • IEEE Transactions on Neural Networks and Learning Systems
  • Zhen Fang +4
  • Conference Article
  • Citations333

Separate to Adapt: Open Set Domain Adaptation via Progressive Separation

  • Jun 01, 2019
  • Hong Liu +4
  • Research Article

Open-Set Domain Adaptation via Target-Relaxed Optimal Transport.

  • Jan 01, 2026
  • IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
  • Chuan-Xian Ren +2
  • Research Article
  • Citations20

Adversarial open set domain adaptation via progressive selection of transferable target samples

  • May 30, 2020
  • Neurocomputing
  • Yuan Gao +4
  • Conference Article
  • Citations28

Joint Partial Optimal Transport for Open Set Domain Adaptation

  • Jul 01, 2020
  • Renjun Xu +7
  • Research Article
  • Citations12

Open-set domain adaptation with visual-language foundation models

  • Nov 19, 2024
  • Computer Vision and Image Understanding
  • Qing Yu +2
  • Book Chapter
  • Citations7

Open Set Domain Adaptation with Entropy Minimization

  • Jan 01, 2020
  • Xiaofu Wu +2
  • Research Article

Open Set Domain Adaptation via Known Joint Distribution Matching and Unknown Classification Risk Reformulation.

  • Jul 01, 2026
  • IEEE transactions on neural networks and learning systems
  • Sentao Chen +2
  • Book Chapter
  • Citations1

Adversarial Learning Approach for Open Set Domain Adaptation

  • Jan 01, 2020
  • Kuniaki Saito +3
  • Research Article
  • Citations105

Adversarial Network With Multiple Classifiers for Open Set Domain Adaptation

  • Aug 13, 2020
  • IEEE Transactions on Multimedia
  • Tasfia Shermin +4
  • Research Article
  • Citations5

Open set domain adaptation with latent structure discovery and kernelized classifier learning

  • Feb 17, 2023
  • Neurocomputing
  • Yongqiang Tang +2
  • Research Article
  • Citations40

Open Set Domain Adaptation With Soft Unknown-Class Rejection.

  • Mar 01, 2023
  • IEEE Transactions on Neural Networks and Learning Systems
  • Yiming Xu +4
  • Research Article

End-to-end open-set domain adaptation for cross-scene remote sensing image classification

  • Apr 22, 2026
  • Remote Sensing Letters
  • Zhendong Zheng +4
  • Conference Article
  • Citations3

Learning Likelihood Estimates for Open Set Domain Adaptation

  • Jul 01, 2020
  • Haiyang Zhang +2
  • Research Article
  • Citations6

Self-Labeling Framework for Open-Set Domain Adaptation With Few Labeled Samples

  • Jan 01, 2024
  • IEEE Transactions on Multimedia
  • Qing Yu +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.