• Home
  • Search
  • Multi-Source Contribution Learning for Domain Adaptation.
  • Cite Icon77
  • https://doi.org/10.1109/tnnls.2021.3069982Copy DOI Icon

Multi-Source Contribution Learning for Domain Adaptation.

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

Transfer learning becomes an attractive technology to tackle a task from a target domain by leveraging previously acquired knowledge from a similar domain (source domain). Many existing transfer learning methods focus on learning one discriminator with single-source domain. Sometimes, knowledge from single-source domain might not be enough for predicting the target task. Thus, multiple source domains carrying richer transferable information are considered to complete the target task. Although there are some previous studies dealing with multi-source domain adaptation, these methods commonly combine source predictions by averaging source performances. Different source domains contain different transferable information; they may contribute differently to a target domain compared with each other. Hence, the source contribution should be taken into account when predicting a target task. In this article, we propose a novel multi-source contribution learning method for domain adaptation (MSCLDA). As proposed, the similarities and diversities of domains are learned simultaneously by extracting multi-view features. One view represents common features (similarities) among all domains. Other views represent different characteristics (diversities) in a target domain; each characteristic is expressed by features extracted in a source domain. Then multi-level distribution matching is employed to improve the transferability of latent features, aiming to reduce misclassification of boundary samples by maximizing discrepancy between different classes and minimizing discrepancy between the same classes. Concurrently, when completing a target task by combining source predictions, instead of averaging source predictions or weighting sources using normalized similarities, the original weights learned by normalizing similarities between source and target domains are adjusted using pseudo target labels to increase the disparities of weight values, which is desired to improve the performance of the final target predictor if the predictions of sources exist significant difference. Experiments on real-world visual data sets demonstrate the superiorities of our proposed method.

Similar Papers
  • Research Article
  • Citations23

Multi-source domain adaptation with graph embedding and adaptive label prediction

  • Aug 18, 2020
  • Information Processing & Management
  • Ao Ma +4
  • Research Article

EDTM: Efficient Domain Transition for Multi-Source Domain Adaptation

  • Jan 01, 2026
  • Computer Modeling in Engineering & Sciences
  • Mangyu Lee +4
  • Research Article
  • Citations45

Universal multi-Source domain adaptation for image classification

  • Aug 14, 2021
  • Pattern Recognition
  • Yueming Yin +3
  • Research Article
  • Citations78

Multi-Source Domain Adaptation for Visual Sentiment Classification

  • Apr 03, 2020
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Chuang Lin +3
  • Conference Article
  • Citations10

Multi-Source Domain Adaptation with Fuzzy-Rule based Deep Neural Networks

  • Jul 11, 2021
  • Keqiuyin Li +3
  • Conference Article
  • Citations65

StandardGAN: Multi-source Domain Adaptation for Semantic Segmentation of Very High Resolution Satellite Images by Data Standardization

  • Jun 01, 2020
  • Onur Tasar +4
  • Research Article
  • Citations41

Dynamic Classifier Alignment for Unsupervised Multi-Source Domain Adaptation

  • Jan 01, 2022
  • IEEE Transactions on Knowledge and Data Engineering
  • Keqiuyin Li +3
  • Research Article
  • Citations79

Attention-Based Multi-Source Domain Adaptation

  • Jan 01, 2021
  • IEEE Transactions on Image Processing
  • Yukun Zuo +2
  • Research Article
  • Citations35

Prototype-Based Multisource Domain Adaptation.

  • Oct 01, 2022
  • IEEE Transactions on Neural Networks and Learning Systems
  • Lihua Zhou +4
  • Research Article

Incomplete Multi-Source Domain Adaptation for Fault Diagnosis of Blast Furnace

  • Jan 01, 2025
  • IEEE Transactions on Instrumentation and Measurement
  • Dali Gao +2
  • Research Article
  • Citations20

Leveraging Mixture Alignment for Multi-Source Domain Adaptation.

  • Jan 01, 2025
  • IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
  • Aveen Dayal +4
  • Research Article
  • Citations117

Multi-Source Unsupervised Domain Adaptation via Pseudo Target Domain.

  • Jan 01, 2022
  • IEEE Transactions on Image Processing
  • Chuan-Xian Ren +3
  • Research Article
  • Citations14

Multi-source adversarial transfer learning for ultrasound image segmentation with limited similarity

  • Jul 26, 2023
  • Applied Soft Computing
  • Yifu Zhang +10
  • Conference Article
  • Citations8

Multi-Source Domain Adaptation with Distribution Fusion and Relationship Extraction

  • Jul 01, 2020
  • Keqiuyin Li +3
  • 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
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.