• Home
  • Search
  • Overcoming learning bias via Prototypical Feature Compensation for source-free domain adaptation
  • Cite Icon16
  • https://doi.org/10.1016/j.patcog.2024.111025Copy DOI Icon

Overcoming learning bias via Prototypical Feature Compensation for source-free domain adaptation

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

The focus of Source-free Unsupervised Domain Adaptation (SFUDA) is to effectively transfer a well-trained model from the source domain to an unlabelled target domain. During the target domain adaptation, the source domain data is no longer accessible. Prevalent methodologies attempt to synchronize the data distributions between the source and target domains, utilizing pseudo-labels to impart categorical information, which has made some progress in improving the model’s performance. However, performance impairments persist due to the introduction of learning bias from the source model and the impact of noisy pseudo-labels generated for the target domain. In this research, we reveal that the central cause for feature misalignment during domain transition is the learning bias, which is generated by the discrepancy of information between source and target domain data. The source domain data may contain distinguishable features that do not appear on the target domain, which causes the pre-trained source model to fail to work during domain adaptation. To overcome the information discrepancy, we propose a Prototypical Feature Compensation (PFC) Network. The network extracts representative feature maps of the source domain. Then use them to minimize the discrepancy information in the target domain feature maps. This mechanism facilitates feature alignment across different domains, allowing the model to generate more accurate categorical data through pseudo-labelling. The experimental results and ablation studies demonstrate exceptional performance on three SFUDA datasets and provide evidence of the proposed PFC method’s ability to adjust the feature distribution of both source and target domain data, ensuring their overlap in the latent space.

Similar Papers
  • Research Article

Systematic Analysis of Source-Free Domain Adaptation Methods

  • Mar 27, 2025
  • Frontiers in Computing and Intelligent Systems
  • Zhiyi Miao
  • Research Article
  • Citations37

Reducing the effect of sample bias for small data sets with double‐weighted support vector transfer regression

  • Sep 01, 2020
  • Computer-Aided Civil and Infrastructure Engineering
  • Huan Luo +1
  • Research Article
  • Citations5

Dual Structural Consistent Partial Domain Adaptation Network for Intelligent Machinery Fault Diagnosis

  • Jan 01, 2024
  • IEEE Transactions on Instrumentation and Measurement
  • Kun Yu +5
  • Conference Article
  • Citations5

Deep Domain Adaptation based Cloud Type Detection using Active and Passive Satellite Data

  • Dec 10, 2020
  • Xin Huang +6
  • Research Article

Fault diagnosis of rolling bearing with variable working conditions in noisy environment based on dynamic soft threshold and attention mechanism

  • Dec 19, 2024
  • Measurement Science and Technology
  • Ankang Li +3
  • Research Article
  • Citations51

A MultiKernel Domain Adaptation Method for Unsupervised Transfer Learning on Cross-Source and Cross-Region Remote Sensing Data Classification

  • Jan 17, 2020
  • IEEE Transactions on Geoscience and Remote Sensing
  • Wei Liu +1
  • Conference Article

Source Free Domain Adaptation via Combined Discriminative GAN Model for Image Classification

  • Jul 18, 2022
  • Yujie Liu +4
  • 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
  • Conference Article
  • Citations3

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

  • Jan 01, 2014
  • Suranjana Samanta +2
  • Research Article
  • Citations34

Adversarial domain adaptation network with pseudo-siamese feature extractors for cross-bearing fault transfer diagnosis

  • May 17, 2022
  • Engineering Applications of Artificial Intelligence
  • Qunwang Yao +4
  • Supplementary Content

On Transfer Learning Techniques for Machine Learning

  • Apr 30, 2020
  • Figshare
  • Debasmit Das
  • Research Article
  • Citations53

Online transfer learning by leveraging multiple source domains

  • Jan 11, 2017
  • Knowledge and Information Systems
  • Qingyao Wu +4
  • Book Chapter
  • Citations1

Unsupervised Domain Adaptation Dictionary Learning for Visual Recognition

  • Jan 01, 2018
  • Zhun Zhong +3
  • Research Article
  • Citations1

A novel Pseudo-label based domain adaptation method on tabular data

  • May 04, 2023
  • Journal of Intelligent & Fuzzy Systems
  • Chu Wang +4
  • Book Chapter
  • Citations8

Domain Adaptation for Eye Segmentation

  • Jan 01, 2020
  • Yiru Shen +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.