• Home
  • Search
  • Multi-Source Distilling Domain Adaptation
  • Cite Icon225
  • https://doi.org/10.1609/aaai.v34i07.6997Copy DOI Icon

Multi-Source Distilling Domain Adaptation

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

Deep neural networks suffer from performance decay when there is domain shift between the labeled source domain and unlabeled target domain, which motivates the research on domain adaptation (DA). Conventional DA methods usually assume that the labeled data is sampled from a single source distribution. However, in practice, labeled data may be collected from multiple sources, while naive application of the single-source DA algorithms may lead to suboptimal solutions. In this paper, we propose a novel multi-source distilling domain adaptation (MDDA) network, which not only considers the different distances among multiple sources and the target, but also investigates the different similarities of the source samples to the target ones. Specifically, the proposed MDDA includes four stages: (1) pre-train the source classifiers separately using the training data from each source; (2) adversarially map the target into the feature space of each source respectively by minimizing the empirical Wasserstein distance between source and target; (3) select the source training samples that are closer to the target to fine-tune the source classifiers; and (4) classify each encoded target feature by corresponding source classifier, and aggregate different predictions using respective domain weight, which corresponds to the discrepancy between each source and target. Extensive experiments are conducted on public DA benchmarks, and the results demonstrate that the proposed MDDA significantly outperforms the state-of-the-art approaches. Our source code is released at: https://github.com/daoyuan98/MDDA.

Similar Papers
  • 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
  • Citations40

Source-Free Multidomain Adaptation With Fuzzy Rule-Based Deep Neural Networks

  • Dec 01, 2023
  • IEEE Transactions on Fuzzy Systems
  • Keqiuyin Li +3
  • Research Article
  • Citations22

Importance-weighted conditional adversarial network for unsupervised domain adaptation

  • Apr 04, 2020
  • Expert Systems with Applications
  • Peng Liu +5
  • Research Article
  • Citations12

Deep reconstruction-recoding network for unsupervised domain adaptation and multi-center generalization in colonoscopy polyp detection

  • Dec 05, 2021
  • Computer Methods and Programs in Biomedicine
  • Jianwei Xu +8
  • Research Article
  • Citations45

Universal multi-Source domain adaptation for image classification

  • Aug 14, 2021
  • Pattern Recognition
  • Yueming Yin +3
  • Book Chapter
  • Citations110

Attract, Perturb, and Explore: Learning a Feature Alignment Network for Semi-supervised Domain Adaptation

  • Jan 01, 2020
  • Taekyung Kim +1
  • Conference Article
  • Citations32

Target-Relevant Knowledge Preservation for Multi-Source Domain Adaptive Object Detection

  • Jun 01, 2022
  • Jiaxi Wu +9
  • Research Article
  • Citations25

Multilevel Heterogeneous Domain Adaptation Method for Remote Sensing Image Segmentation

  • Jan 01, 2023
  • IEEE Transactions on Geoscience and Remote Sensing
  • Chenbin Liang +4
  • Book Chapter
  • Citations3

On the Application of Partial Domain Adaptation for PBSHM

  • Jun 22, 2022
  • Jack Poole +4
  • Research Article
  • Citations31

Multi-source domain generalization and adaptation toward cross-subject myoelectric pattern recognition

  • Feb 01, 2023
  • Journal of Neural Engineering
  • Xuan Zhang +5
  • Research Article
  • Citations2

Toward Open-World Domain Adaptation via Iteratively Contrastive Learning and Clustering.

  • Jan 01, 2025
  • IEEE transactions on neural networks and learning systems
  • Jingzheng Li +4
  • Research Article
  • Citations9

Similarity-based domain adaptation network

  • Dec 31, 2021
  • Neurocomputing
  • Meixin Peng +2
  • Research Article
  • Citations3

An iterative-cluster domain adaptation fault diagnosis method for incremental multi-target domain adaptation

  • Feb 25, 2025
  • Measurement Science and Technology
  • Cheng Wang +2
  • Dissertation

Towards robust sensing and recognition : from statistical learning to transfer learning

  • Jan 01, 2020
  • Jianfei Yang
  • Research Article
  • Citations1

Metric‐guided class‐level alignment for domain adaptation

  • Dec 15, 2024
  • IET Computer Vision
  • Xiaoshun Wang +1
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.