• Home
  • Search
  • Joint Clustering and Discriminative Feature Alignment for Unsupervised Domain Adaptation.
  • Open Access IconOpen Access
  • Cite Icon53
  • https://doi.org/10.1109/tip.2021.3109530Copy DOI Icon

Joint Clustering and Discriminative Feature Alignment for Unsupervised Domain Adaptation.

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

Unsupervised Domain Adaptation (UDA) aims to learn a classifier for the unlabeled target domain by leveraging knowledge from a labeled source domain with a different but related distribution. Many existing approaches typically learn a domain-invariant representation space by directly matching the marginal distributions of the two domains. However, they ignore exploring the underlying discriminative features of the target data and align the cross-domain discriminative features, which may lead to suboptimal performance. To tackle these two issues simultaneously, this paper presents a Joint Clustering and Discriminative Feature Alignment (JCDFA) approach for UDA, which is capable of naturally unifying the mining of discriminative features and the alignment of class-discriminative features into one single framework. Specifically, in order to mine the intrinsic discriminative information of the unlabeled target data, JCDFA jointly learns a shared encoding representation for two tasks: supervised classification of labeled source data, and discriminative clustering of unlabeled target data, where the classification of the source domain can guide the clustering learning of the target domain to locate the object category. We then conduct the cross-domain discriminative feature alignment by separately optimizing two new metrics: 1) an extended supervised contrastive learning, i.e., semi-supervised contrastive learning 2) an extended Maximum Mean Discrepancy (MMD), i.e., conditional MMD, explicitly minimizing the intra-class dispersion and maximizing the inter-class compactness. When these two procedures, i.e., discriminative features mining and alignment are integrated into one framework, they tend to benefit from each other to enhance the final performance from a cooperative learning perspective. Experiments are conducted on four real-world benchmarks (e.g., Office-31, ImageCLEF-DA, Office-Home and VisDA-C). All the results demonstrate that our JCDFA can obtain remarkable margins over state-of-the-art domain adaptation methods. Comprehensive ablation studies also verify the importance of each key component of our proposed algorithm and the effectiveness of combining two learning strategies into a framework.

Similar Papers
  • Conference Article
  • Citations1

Transferable Discriminative Feature Mining For Unsupervised Domain Adaptation

  • Sep 19, 2021
  • Lingjun Zhao +4
  • Research Article
  • Citations37

Unsupervised Adversarial Domain Adaptation Network for Semantic Segmentation

  • Dec 26, 2019
  • IEEE Geoscience and Remote Sensing Letters
  • Wei Liu +1
  • 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
  • Citations45

Universal multi-Source domain adaptation for image classification

  • Aug 14, 2021
  • Pattern Recognition
  • Yueming Yin +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
  • Citations5

Domain‐specific feature recalibration and alignment for multi‐source unsupervised domain adaptation

  • Aug 27, 2022
  • IET Computer Vision
  • Mengzhu Wang +6
  • Research Article
  • Citations49

IF-EDAAN: An information fusion-enhanced domain adaptation attention network for unsupervised transfer fault diagnosis

  • Feb 01, 2025
  • Mechanical Systems and Signal Processing
  • Cuiying Lin +8
  • Research Article
  • Citations10

Deep joint subdomain alignment for unsupervised domain adaptation

  • Mar 01, 2025
  • Expert Systems With Applications
  • Zhenze Zhong +3
  • Research Article
  • Citations30

Unsupervised adversarial domain adaptation with similarity diffusion for person re-identification

  • Dec 16, 2020
  • Neurocomputing
  • Geyu Tang +3
  • Conference Article
  • Citations94

Multi-Target Domain Adaptation with Collaborative Consistency Learning

  • Jun 01, 2021
  • Takashi Isobe +7
  • Conference Article
  • Citations1

Integration of Discriminate Features and Similarity Preserving for Unsupervised Domain Adaptation

  • Nov 24, 2022
  • Obsa Gilo +2
  • Conference Article
  • Citations3

Modeling Sequential Domain Shift through Estimation of Optimal Sub-spaces for Categorization

  • Jan 01, 2014
  • Suranjana Samanta +2
  • Conference Article
  • Citations6

A simple approach for unsupervised domain adaptation

  • Dec 01, 2016
  • Xifeng Guo +2
  • Dissertation

Label-efficient visual recognition with transfer learning

  • Jan 01, 2025
  • Jingyi Zhang
  • Research Article
  • Citations2

Towards Discriminative Class-Aware Domain Alignment via Coding Rate Reduction for Unsupervised Adversarial Domain Adaptation

  • Sep 16, 2024
  • Symmetry
  • Jiahua Wu +1
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.