• Home
  • Search
  • A Versatile Framework for Unsupervised Domain Adaptation based on Instance Weighting.
  • Cite Icon8
  • https://doi.org/10.1109/tip.2024.3486617Copy DOI Icon

A Versatile Framework for Unsupervised Domain Adaptation based on Instance Weighting.

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

Despite the progress made in domain adaptation, solving Unsupervised Domain Adaptation (UDA) problems with a general method under complex conditions caused by label shifts between domains remains a challenging task. In this work, we comprehensively investigate four distinct UDA settings including closed set domain adaptation, partial domain adaptation, open set domain adaptation, and universal domain adaptation, where shared common classes between source and target domains coexist alongside domain-specific private classes. The prominent challenges inherent in diverse UDA settings center around the discrimination of common/private classes and the precise measurement of domain discrepancy. To surmount these challenges effectively, we propose a novel yet effective method called Learning Instance Weighting for Unsupervised Domain Adaptation (LIWUDA), which caters to various UDA settings. Specifically, the proposed LIWUDA method constructs a weight network to assign weights to each instance based on its probability of belonging to common classes, and designs Weighted Optimal Transport (WOT) for domain alignment by leveraging instance weights. Additionally, the proposed LIWUDA method devises a Separate and Align (SA) loss to separate instances with low similarities and align instances with high similarities. To guide the learning of the weight network, Intra-domain Optimal Transport (IOT) is proposed to enforce the weights of instances in common classes to follow a uniform distribution. Through the integration of those three components, the proposed LIWUDA method demonstrates its capability to address all four UDA settings in a unified manner. Experimental evaluations conducted on four benchmark datasets substantiate the effectiveness of the proposed LIWUDA method. The code is available at https://github.com/JinjingZhu/LIWUDA.

Similar Papers
  • Research Article
  • Citations2

Heterogeneous domain adaptation for intracortical signal classification using domain consensus

  • Dec 29, 2022
  • Biomedical Signal Processing and Control
  • Yuanrui Dong +3
  • Research Article
  • Citations43

An ensemble and shared selective adversarial network for partial domain fault diagnosis of machinery

  • May 10, 2022
  • Engineering Applications of Artificial Intelligence
  • Xiaoyang Liu +4
  • 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
  • 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
  • Research Article
  • Citations31

HyUniDA: Breaking Label Set Constraints for Universal Domain Adaptation in Cross-Scene Hyperspectral Image Classification

  • Jan 01, 2024
  • IEEE Transactions on Geoscience and Remote Sensing
  • Qingmei Li +4
  • Research Article
  • Citations31

General feature spatial location and distance-based unknown Detection: A universal domain adaptation fault diagnosis framework of rotating Machinery

  • Dec 07, 2023
  • Mechanical Systems and Signal Processing
  • Yunjia Dong +3
  • Research Article
  • Citations45

A universal transfer network for machinery fault diagnosis

  • Jun 20, 2023
  • Computers in Industry
  • Xiaolei Yu +6
  • Research Article
  • Citations50

Partial Transfer Fault Diagnosis by Multiscale Weight-Selection Adversarial Network

  • Dec 01, 2022
  • IEEE/ASME Transactions on Mechatronics
  • Quan Qian +3
  • Research Article
  • Citations99

A Stacked Auto-Encoder Based Partial Adversarial Domain Adaptation Model for Intelligent Fault Diagnosis of Rotating Machines

  • Dec 15, 2020
  • IEEE Transactions on Industrial Informatics
  • Zhao-Hua Liu +5
  • Research Article
  • Citations2

Extending Partial Domain Adaptation Algorithms to the Open-Set Setting

  • Oct 06, 2022
  • Applied Sciences
  • George Pikramenos +2
  • PDF
  • Research Article

Providing Domain Specific Model via Universal No Data Exchange Domain Adaptation

  • Mar 01, 2021
  • Journal of Physics: Conference Series
  • Lixu Wang +2
  • Book Chapter
  • Citations1

Adversarial Learning Approach for Open Set Domain Adaptation

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

Tight Source Domain Match for Partial Domain Adaptation Based on Maximum Density

  • May 01, 2022
  • Journal of Physics Conference Series
  • Zi-Ao Ni +4
  • Research Article

An open-set domain adaptation approach for cross-region crop mapping

  • Mar 28, 2026
  • International Journal of Remote Sensing
  • Yijia Xu +1
  • Research Article
  • Citations15

Manifold discrimination partial adversarial domain adaptation

  • Jun 25, 2022
  • Knowledge-Based Systems
  • Chunmei He +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.