• Home
  • Search
  • Progressive Source-Aware Transformer for Generalized Source-Free Domain Adaptation
  • Cite Icon11
  • https://doi.org/10.1109/tmm.2023.3321421Copy DOI Icon

Progressive Source-Aware Transformer for Generalized Source-Free Domain Adaptation

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

Source-free domain adaptation (SFDA) tends to forget the source domain, suffering from limitations in real-world scenarios. Recently, generalized source-free domain adaptation (GSFDA) problem naturally emerges, aiming for good performance on both target and source domains. The existing methods attempt to retain model parameters associated with the source domain to prevent such forgetting. However, this strategy is not conducive to improving cross-domain performance on the target domain, prioritizing mitigating forgetting on the source domain. This article introduces a Progressive Source-Aware Transformer approach for GSFDA, dubbed PSAT-GDA. Our core idea is to enforce the domain adaptation process to remember the source domain by imposing source guidance, offering a target domain-centric anti-forgetting mechanism. Specifically, for each epoch, a Transformer-based deep network is adapted to do domain alignment like the traditional SFDA method, because the transformer working on the image patch sequence helps to reduce image noise caused by domain shift. Meanwhile, another Transformer is designed to generate source guidance supervising domain alignment. By augmenting target sample and mining the source information from the historical models before current epoch, source injected feature group is constructed. Based on the Transformer mechanism, the attention block can select useful source information for each target sample. From it, we devise neighbour-based and augmentation-based regularizations to shape the source guidance. Experiments on three challenging datasets show that our method can achieve evident cross-domain improvement on the target domains. Also, it can mitigate forgetting on all domains after adapting to single or multiple target domains.

Similar Papers
  • Dissertation

Towards robust sensing and recognition : from statistical learning to transfer learning

  • Jan 01, 2020
  • Jianfei Yang
  • Research Article
  • Citations20

Self-Supervised Auxiliary Domain Alignment for Unsupervised 2D Image-Based 3D Shape Retrieval

  • Dec 01, 2022
  • IEEE Transactions on Circuits and Systems for Video Technology
  • An-An Liu +5
  • Research Article
  • Citations52

Deep Asymmetric Transfer Network for Unbalanced Domain Adaptation

  • Apr 25, 2018
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Daixin Wang +2
  • Research Article
  • Citations15

Easy-to-Hard Structure for Remote Sensing Scene Classification in Multitarget Domain Adaptation

  • Jan 01, 2023
  • IEEE Transactions on Geoscience and Remote Sensing
  • Ba Hung Ngo +4
  • Conference Article
  • Citations4

Machine Learning Pipeline for Reusing Pretrained Models

  • Nov 02, 2020
  • Maryam Alshehhi +1
  • Conference Article
  • Citations35

Unsupervised domain adaptation using parallel transport on Grassmann manifold

  • Mar 01, 2014
  • Ashish Shrivastava +2
  • Research Article
  • Citations4

Toward Unsupervised Domain Adaptation Fault Diagnosis: A Multisource Multitarget Method

  • Jan 01, 2025
  • IEEE Sensors Journal
  • Zixuan Wang +8
  • Research Article
  • Citations141

Heterogeneous Graph Attention Network for Unsupervised Multiple-Target Domain Adaptation.

  • Sep 23, 2020
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • Xu Yang +3
  • Research Article
  • Citations45

Universal multi-Source domain adaptation for image classification

  • Aug 14, 2021
  • Pattern Recognition
  • Yueming Yin +3
  • Conference Article
  • Citations250

Generalized Source-free Domain Adaptation

  • Oct 01, 2021
  • Shiqi Yang +4
  • Book Chapter
  • Citations28

Discriminative Partial Domain Adversarial Network

  • Jan 01, 2020
  • Jian Hu +7
  • Research Article
  • Citations4

Enhancing Cross-Domain Remote Sensing Scene Classification by Multi-Source Subdomain Distribution Alignment Network

  • Apr 05, 2025
  • Remote Sensing
  • Yong Wang +6
  • Research Article
  • Citations27

Multi-Source Collaborative Contrastive Learning for Decentralized Domain Adaptation

  • May 01, 2023
  • IEEE Transactions on Circuits and Systems for Video Technology
  • Yikang Wei +3
  • Conference Article
  • Citations15

Domain adaptation based on deep denoising auto-encoders for classification of remote sensing images

  • Oct 18, 2016
  • Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE
  • Emanuele Riz +2
  • Conference Article

Class-Level Adaptation Network with Self Training for Unsupervised Domain Adaptation

  • Dec 02, 2019
  • Yuncheng Jin +5
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.