• Home
  • Search
  • Discriminative Invariant Alignment for Unsupervised Domain Adaptation
  • Cite Icon67
  • https://doi.org/10.1109/tmm.2021.3073258Copy DOI Icon

Discriminative Invariant Alignment for Unsupervised Domain Adaptation

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

As one of the most prevalent branches of transfer learning, domain adaptation is dedicated to generalizing the knowledge of a source domain to a target domain to perform machine learning tasks. In domain adaptation, the key strategy is to overcome the shift between different domains and learn shared features with domain invariance. However, most existing methods focus on extracting the common features of the source and target domains, and do not consider the shift problem of class center in the target domain caused by this process. Specifically, when we align the domain distributions, we often ignore the inherent feature attributes of the data, or under the guidance of false pseudo-labels, cause the target domain data to be far away from the class center after projection. This is not conducive to classification task. To address these problems, in this study, we propose a novel domain adaptation method, referred to as discriminative invariant alignment (DIA), for image representation. DIA enriches the knowledge matrix by combining the class discriminative information of the source domain and local data structure information of the target domain into a new framework. By introducing the maximum margin criterion of the source domain, the classification boundaries are expanded. To verify the performance of the proposed method, we compared DIA with several state-of-the-art methods on five benchmark databases. The experimental results show that DIA is superior to the state-of-the-art methods.

Similar Papers
  • Conference Article
  • Citations15

Healing Sample Selection Bias by Source Classifier Selection

  • Dec 01, 2011
  • Chun-Wei Seah +2
  • Research Article
  • Citations30

Easy Domain Adaptation for cross-subject multi-view emotion recognition

  • Dec 21, 2021
  • Knowledge-Based Systems
  • Chuangquan Chen +4
  • Research Article
  • Citations11

Joint predictive model and representation learning for visual domain adaptation

  • Dec 14, 2016
  • Engineering Applications of Artificial Intelligence
  • Marzieh Gheisari +1
  • PDF
  • Research Article

Learning Transferable Convolutional Proxy by SMI-Based Matching Technique

  • Oct 14, 2020
  • Shock and Vibration
  • Wei Jin +1
  • Book Chapter
  • Citations2

Domain Adaptation for Document Classification by Alternately Using Semi-supervised Learning and Feature Weighted Learning

  • Jan 01, 2018
  • Hiroyuki Shinnou +2
  • Conference Article
  • Citations8

Learning Target Predictive Function without Target Labels

  • Dec 01, 2012
  • Chun-Wei Seah +3
  • Supplementary Content

On Transfer Learning Techniques for Machine Learning

  • Apr 30, 2020
  • Figshare
  • Debasmit Das
  • 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
  • Citations61

Combating Negative Transfer From Predictive Distribution Differences.

  • Aug 01, 2013
  • IEEE Transactions on Cybernetics
  • Chun-Wei Seah +2
  • PDF
  • Research Article
  • Citations8

Online Domain Adaptation for Rolling Bearings Fault Diagnosis with Imbalanced Cross-Domain Data.

  • Jun 16, 2022
  • Sensors
  • Ko-Chieh Chao +2
  • PDF
  • Research Article
  • Citations1

A Fault Detection Approach Based on One-Sided Domain Adaptation and Generative Adversarial Networks for Railway Door Systems

  • Dec 07, 2023
  • Sensors (Basel, Switzerland)
  • Minoru Shimizu +2
  • Research Article
  • Citations5

Easy-to-Hard Domain Adaptation With Human Interaction for Hyperspectral Image Classification

  • Jan 01, 2024
  • IEEE Transactions on Geoscience and Remote Sensing
  • Cheng Zhang +3
  • Research Article
  • Citations12

A complex process fault diagnosis method based on manifold distribution adaptation

  • Oct 15, 2019
  • Engineering Applications of Artificial Intelligence
  • Xiaogang Wang +1
  • Research Article
  • Citations378

Domain adaptation from multiple sources: a domain-dependent regularization approach.

  • Mar 01, 2012
  • IEEE Transactions on Neural Networks and Learning Systems
  • Lixin Duan +2
  • PDF
  • Conference Article
  • Citations22

Open-Ended Visual Question Answering by Multi-Modal Domain Adaptation

  • Jan 01, 2020
  • Yiming Xu +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.