• Home
  • Search
  • Dual-Level Adaptive and Discriminative Knowledge Transfer for Cross-Domain Recognition
  • Cite Icon22
  • https://doi.org/10.1109/tmm.2022.3145235Copy DOI Icon

Dual-Level Adaptive and Discriminative Knowledge Transfer for Cross-Domain Recognition

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

Unsupervised domain adaptation is an appealing technique to learn robust classifiers for unlabeled target domain by borrowing knowledge from well-established source domain. However, previous works mainly suffer from two limitations: 1) the classifier trained on labeled source data may be prone to overfitting the source distribution, lowering its performance on the target domain; 2) the adaptation process will be misled by conditional distribution matching using hard pseudo labels of target samples. This paper presents a Dual-Level Adaptive and Discriminative (DLAD) classifier learning framework, in which transfer classifier and distribution adaptation can be mutually beneficial for effective knowledge transfer. Specifically, we aim to achieve a domain-level adaptive classifier by considering structural risk minimization (SRM) on both domains and performing weighted distribution adaptation, which facilitates joint classifier learning in a semi-supervised manner. To further achieve a class-level discriminative classifier, we explicitly leverage unlabeled target data to promote classifier learning based on class probabilities, which refines the decision boundary to be more discriminative for unlabeled target data. To the best of our knowledge, DLAD is the first attempt to consider the principle of SRM on the target domain, which significantly boosts the discriminative power of transfer classifier and yields a tighter generalization bound. Experimental evaluations on several standard cross-domain datasets show that DLAD significantly outperforms other competitive methods.

Similar Papers
  • Research Article

Few-Shot Unsupervised Domain Adaptation Based on Refined Bi-Directional Prototypical Contrastive Learning for Cross-Scene Hyperspectral Image Classification

  • Jul 04, 2025
  • Remote Sensing
  • Xuebin Tang +6
  • Conference Article
  • Citations22

Continual Unsupervised Domain Adaptation for Semantic Segmentation by Online Frequency Domain Style Transfer

  • Sep 19, 2021
  • Jan-Aike Termohlen +4
  • Dissertation

Label-efficient visual recognition with transfer learning

  • Jan 01, 2025
  • Jingyi Zhang
  • Research Article
  • Citations114

Multisource Heterogeneous Unsupervised Domain Adaptation via Fuzzy Relation Neural Networks

  • Aug 20, 2020
  • IEEE Transactions on Fuzzy Systems
  • Feng Liu +2
  • Research Article
  • Citations13

Extreme Learning Machine Based on Maximum Weighted Mean Discrepancy for Unsupervised Domain Adaptation

  • Dec 25, 2020
  • IEEE Access
  • Yanna Si +3
  • PDF
  • Research Article
  • Citations9

Adversarial Learning and Interpolation Consistency for Unsupervised Domain Adaptation

  • Jan 01, 2019
  • IEEE Access
  • Xin Zhao +1
  • Research Article
  • Citations6

Semantically preserving adversarial unsupervised domain adaptation network for improving disease recognition from chest x-rays.

  • Jul 01, 2023
  • Computerized Medical Imaging and Graphics
  • Xiaoli Qin +2
  • Research Article
  • Citations19

Source-Free Domain Adaptive Detection of Concealed Objects in Passive Millimeter-Wave Images

  • Jan 01, 2023
  • IEEE Transactions on Instrumentation and Measurement
  • Hao Yang +5
  • Research Article
  • Citations12

Unsupervised Domain Adaptation via Discriminative Classes-Center Feature Learning in Adversarial Network

  • May 21, 2020
  • Neural Processing Letters
  • Wendong Chen +1
  • Research Article
  • Citations154

Unsupervised Domain Adaptation via Disentangled Representations: Application to Cross-Modality Liver Segmentation.

  • Jan 01, 2019
  • Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention
  • Junlin Yang +5
  • Conference Article
  • Citations104

Uncertainty Reduction for Model Adaptation in Semantic Segmentation

  • Jun 01, 2021
  • Prabhu Teja S +1
  • Research Article
  • Citations20

A novel unsupervised Globality-Locality Preserving Projections in transfer learning

  • Aug 25, 2019
  • Image and Vision Computing
  • Rakesh Kumar Sanodiya +1
  • Research Article
  • Citations9

Superpixel-guided class-level denoising for unsupervised domain adaptive fundus image segmentation without source data

  • May 26, 2023
  • Computers in Biology and Medicine
  • Meng Zhou +2
  • Book Chapter
  • Citations45

Dual-Teacher: Integrating Intra-domain and Inter-domain Teachers for Annotation-Efficient Cardiac Segmentation

  • Jan 01, 2020
  • Kang Li +3
  • Conference Article
  • Citations521

Model Adaptation: Unsupervised Domain Adaptation Without Source Data

  • Jun 01, 2020
  • Rui Li +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.