• Home
  • Search
  • SoFA: Source-data-free Feature Alignment for Unsupervised Domain Adaptation
  • Cite Icon78
  • https://doi.org/10.1109/wacv48630.2021.00052Copy DOI Icon

SoFA: Source-data-free Feature Alignment for Unsupervised Domain Adaptation

  • Jan 1, 2021
  • Hao-Wei Yeh +3 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Applying a trained model on a new scenario may suffer from domain shift. Unsupervised domain adaptation (UDA) has been proven to be an effective approach to solve the problem of domain shift by leveraging both data from the scenario that the model was trained on (source) and the new scenario (target). Although the source data are available for training the source model, there is no guarantee that the source data will still be available when applying UDA in the future due to emerging regulations on privacy of data. This results in the in-applicability of most existing UDA methods in the absence of source data. This paper proposes a source-data-free feature alignment (SoFA) method to address this problem by only using the trained source model and unlabeled target data. The source model is used to predict the labels for target data, and we model the generation process from predicted classes to input data to infer the latent features for alignment. Specifically, a mixture of Gaussian distributions is induced from the predicted classes as the reference distribution. The encoded target features are then aligned to the reference distribution via variational inference to extract class semantics without accessing source data. Relationship of the proposed method and the theory of domain adaptation is provided to verify the performance. Experimental results show the proposed method achieves higher or comparable accuracy compared to the existing methods in several cross-dataset classification tasks. Ablation studies are also conducted to confirm the importance of latent feature alignment to adaptation performance.

Similar Papers
  • PDF
  • Research Article
  • Citations3

SFDA-CD: A Source-Free Unsupervised Domain Adaptation for VHR Image Change Detection

  • Apr 04, 2024
  • Remote Sensing
  • Jingxuan Wang +1
  • Book Chapter
  • Citations25

Self Domain Adapted Network

  • Jan 01, 2020
  • Yufan He +4
  • Dissertation

Label-efficient visual recognition with transfer learning

  • Jan 01, 2025
  • Jingyi Zhang
  • Research Article
  • Citations16

Model-Induced Generalization Error Bound for Information-Theoretic Representation Learning in Source-Data-Free Unsupervised Domain Adaptation.

  • Jan 01, 2022
  • IEEE Transactions on Image Processing
  • Baoyao Yang +3
  • Research Article
  • Citations3

Unsupervised global-local domain adaptation with self-training for remote sensing image semantic segmentation

  • Jan 20, 2025
  • International Journal of Remote Sensing
  • Junbo Zhang +3
  • Research Article
  • Citations15

Unsupervised domain adaptation without source data for estimating occupancy and recognizing activities in smart buildings

  • Dec 01, 2023
  • Energy and Buildings
  • Jawher Dridi +2
  • Preprint Article

Segmentation Cycle-GAN Loss for Structure-Preserving Domain Adaptation of Medical Images

  • Sep 06, 2024
  • Paolo Iacono
  • Preprint Article

Segmentation Cycle-GAN Loss for Structure-Preserving Domain Adaptation of Medical Images

  • Sep 06, 2024
  • Paolo Iacono
  • Book Chapter
  • Citations1

Unsupervised Graph Domain Adaptation for Neurodevelopmental Disorders Diagnosis

  • Jan 01, 2020
  • Bomin Wang +7
  • Conference Article
  • Citations145

Unsupervised Multi-source Domain Adaptation Without Access to Source Data

  • Jun 01, 2021
  • Sk Miraj Ahmed +4
  • Book Chapter
  • Citations94

Source-Free Domain Adaptive Fundus Image Segmentation with Denoised Pseudo-Labeling

  • Jan 01, 2021
  • Cheng Chen +4
  • PDF
  • Research Article
  • Citations16

Unsupervised Black-Box Model Domain Adaptation for Brain Tumor Segmentation.

  • Jun 02, 2022
  • Frontiers in neuroscience
  • Xiaofeng Liu +6
  • Abstract

Unsupervised Domain Adaptation of Auto-Segmentation on Multi-Source MRIs

  • Sep 29, 2023
  • International Journal of Radiation Oncology*Biology*Physics
  • W Zhang +4
  • Research Article

Contrastive adapter training and consensus knowledge distillation for multi-source-free domain adaptation in skin cancer diagnosis.

  • Oct 01, 2026
  • Artificial intelligence in medicine
  • Ali Abedi +3
  • 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
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.