• Home
  • Search
  • Universal Domain Alignment Framework for Classification and Regression Tasks
  • Cite Icon3
  • https://doi.org/10.1109/tai.2025.3594315Copy DOI Icon

Universal Domain Alignment Framework for Classification and Regression Tasks

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

Unsupervised Domain Adaptation (UDA), a critical technique for transferring knowledge from labeled source domains to unlabeled target domains, holds significant value in both classification and regression tasks. However, existing methods are often designed for a single task, lacking a unified framework that can handle both types of tasks simultaneously. Moreover, while global distribution alignment can reduce the overall discrepancy between the source and target domains, inconsistencies in local feature spaces persist. These local inconsistencies may introduce biases in high-level semantic structures, increasing the variability of feature distributions and significantly weakening the model’s generalization ability in the target domain. To address these challenges, we propose a Universal Domain Alignment Framework (UDAF), which achieves unified modeling for classification and regression tasks while reducing local distribution discrepancies through the Target Space Coupling Module (TSCM) and the Domain Embedding Consistency Loss (DECL). In UDAF, TSCM optimizes the structure of the output space to meet the requirements of both classification and regression tasks. Specifically, for labeled source domain data, we minimize the distance between features and their corresponding class centers to cluster similar samples in the output space. For unlabeled target domain data, pseudo labels are generated using prediction probabilities to estimate target class centers, and the class centers are dynamically updated to optimize the output space structure. Meanwhile, DECL models local feature alignment from a sample-to-domain perspective. By measuring the distance between target domain samples and the orthogonal basis of source domain subspaces, DECL explicitly captures local distribution biases and incorporates them as optimization objectives, further enhancing the fine-grained alignment of cross-domain features. The proposed UDAF is highly extensible and can be seamlessly integrated into existing methods. Comprehensive experiments conducted on seven datasets demonstrate that this approach achieves a performance improvement, especially with an 2.1% improvement on DomainNet dataset.

Similar Papers
  • Research Article
  • Citations25

ACT: Semi-supervised Domain-adaptive Medical Image Segmentation with Asymmetric Co-Training.

  • Jan 01, 2022
  • Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention
  • Xiaofeng Liu +6
  • Research Article
  • Citations45

Universal multi-Source domain adaptation for image classification

  • Aug 14, 2021
  • Pattern Recognition
  • Yueming Yin +3
  • 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
  • Citations12

Domain adaptive remote sensing image semantic segmentation with prototype guidance

  • Mar 06, 2024
  • Neurocomputing
  • Wankang Zeng +6
  • Dissertation

Label-efficient visual recognition with transfer learning

  • Jan 01, 2025
  • Jingyi Zhang
  • Research Article
  • Citations27

Multi-Source Collaborative Contrastive Learning for Decentralized Domain Adaptation

  • May 01, 2023
  • IEEE Transactions on Circuits and Systems for Video Technology
  • Yikang Wei +3
  • Research Article

Unlocking Cross-Domain Synergies for Domain Adaptive Semantic Segmentation.

  • Jan 01, 2025
  • IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
  • Qin Xu +5
  • Research Article
  • Citations42

Memory consistent unsupervised off-the-shelf model adaptation for source-relaxed medical image segmentation.

  • Jan 01, 2023
  • Medical image analysis
  • Xiaofeng Liu +3
  • Research Article
  • Citations141

Heterogeneous Graph Attention Network for Unsupervised Multiple-Target Domain Adaptation.

  • Sep 23, 2020
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • Xu Yang +3
  • Research Article

Adaptive integrated weight unsupervised multi-source domain adaptation without source data

  • Apr 22, 2025
  • Complex & Intelligent Systems
  • Zhirui Wang +2
  • 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
  • Citations7

Unsupervised Domain Expansion for Visual Categorization

  • Nov 12, 2021
  • ACM Transactions on Multimedia Computing, Communications, and Applications
  • Jie Wang +4
  • Research Article
  • Citations46

A Self-Supervised-Driven Open-Set Unsupervised Domain Adaptation Method for Optical Remote Sensing Image Scene Classification and Retrieval

  • Jan 01, 2023
  • IEEE Transactions on Geoscience and Remote Sensing
  • Siyuan Wang +2
  • Research Article
  • Citations4

Enhancing unsupervised fault diagnosis method for rolling bearings using domain adaptive transfer coding techniques

  • May 27, 2025
  • Measurement Science and Technology
  • Jiantao Lu +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.