• Home
  • Search
  • Toward Improving Robustness and Accuracy in Unsupervised Domain Adaptation
  • Cite Icon2
  • https://doi.org/10.1609/aaai.v39i7.32750Copy DOI Icon

Toward Improving Robustness and Accuracy in Unsupervised Domain Adaptation

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

Adversarial robustness in the context of Unsupervised Domain Adaptation (UDA) is particularly challenging due to the lack of labels in the target domain. Pseudo labels are often used to make adversarial robust models but compromise robustness and accuracy, falling short of the performance due to noise and inaccuracies in these pseudo labels. The main challenges in achieving robustness and accuracy include ensuring reliable pseudo labels and developing effective training methods that bring alignment between clean and adversarial examples of target data. To address these challenges, we propose a novel training method within the self-training paradigm Consistent Attention Mapping with Self Pseudo Label Refinement (CAM+SPLR). It begins with the pre-training of the UDA model, resulting in a UDA pre-trained model, which is initialized into two separate models: the Anchor model and the TargetNet model. The Anchor model encourages the attention maps of clean images and their adversarial counterparts to be similar, while the TargetNet model simultaneously performs self-training using Adversarial target data and refining the pseudo labels. CAM+SPLR improves both semantically relevant key features and pseudo-labels through a two-step stochastic gradient descent process during training. We conducted extensive experiments on benchmark datasets, including OfficeHome, PACS, and VisDA, demonstrating significant improvements in both robustness and accuracy. Our method achieves an average accuracy improvement of 6% and 8.1% and an average robustness improvement of 10.2% and 4.9%, compared to state-of-the-art methods on the PACS and VisDA datasets.

Similar Papers
  • Book Chapter

A Step Towards Robust Unsupervised Domain Adaptation via Fine-Tuning and Reinforcement Learning

  • Oct 21, 2025
  • Frontiers in artificial intelligence and applications
  • Sushant Dagaji Desale +2
  • Research Article
  • Citations11

SRoUDA: Meta Self-Training for Robust Unsupervised Domain Adaptation

  • Jun 26, 2023
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Wanqing Zhu +3
  • Research Article
  • Citations42

Improving pseudo labels with intra-class similarity for unsupervised domain adaptation

  • Feb 02, 2023
  • Pattern Recognition
  • Jie Wang +1
  • Research Article

Tight Source Domain Match for Partial Domain Adaptation Based on Maximum Density

  • May 01, 2022
  • Journal of Physics Conference Series
  • Zi-Ao Ni +4
  • Research Article
  • Citations15

Unsupervised Multitarget Domain Adaptation With Dictionary-Bridged Knowledge Exploitation.

  • Mar 01, 2024
  • IEEE Transactions on Neural Networks and Learning Systems
  • Qing Tian +5
  • Research Article
  • Citations27

Pseudo-labeling Integrating Centers and Samples with Consistent Selection Mechanism for Unsupervised Domain Adaptation

  • Jan 30, 2023
  • Information Sciences
  • Lei Li +3
  • Conference Article
  • Citations31

Adversarial Robustness for Unsupervised Domain Adaptation

  • Oct 01, 2021
  • Muhammad Awais +6
  • Research Article
  • Citations9

Teacher–Student Mutual Learning for efficient source-free unsupervised domain adaptation

  • Dec 14, 2022
  • Knowledge-Based Systems
  • Wei Li +2
  • Research Article
  • Citations43

Pseudo Labels for Unsupervised Domain Adaptation: A Review

  • Aug 03, 2023
  • Electronics
  • Yundong Li +2
  • Research Article

Adaptive integrated weight unsupervised multi-source domain adaptation without source data

  • Apr 22, 2025
  • Complex & Intelligent Systems
  • Zhirui Wang +2
  • Research Article
  • Citations31

FPL+: Filtered Pseudo Label-Based Unsupervised Cross-Modality Adaptation for 3D Medical Image Segmentation.

  • Sep 01, 2024
  • IEEE transactions on medical imaging
  • Jianghao Wu +6
  • Research Article
  • Citations13

Source-free domain adaptation via dynamic pseudo labeling and Self-supervision

  • Jul 22, 2024
  • Pattern Recognition
  • Qiankun Ma +7
  • Research Article
  • Citations5

Unsupervised cross-domain person re-identification with self-attention and joint-flexible optimization

  • Apr 30, 2021
  • Image and Vision Computing
  • Haopeng Hou +6
  • Conference Article
  • Citations2

Source-Free Unsupervised Domain Adaptation via Denoising Mutual Learning

  • Dec 16, 2022
  • Zhang Hao +1
  • Research Article
  • Citations30

Information Maximizing Adaptation Network With Label Distribution Priors for Unsupervised Domain Adaptation

  • Jan 01, 2023
  • IEEE Transactions on Multimedia
  • Pei Wang +5
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.