• Home
  • Search
  • A Step Towards Robust Unsupervised Domain Adaptation via Fine-Tuning and Reinforcement Learning
  • https://doi.org/10.3233/faia251076Copy DOI Icon

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

Show More
  • Abstract
  • Literature Map
  • Similar Papers
Abstract

Adversarial robustness in Unsupervised Domain Adaptation (UDA) remains a significant challenge due to noisy pseudo labels and inherent distributional shifts between the clean source and adversarially perturbed target domains. Existing approaches often fail to achieve an optimal trade-off between robustness and accuracy, as pseudo-labels generated by domain-adapted models tend to introduce classification errors under adversarial attacks. In this work, we propose SFT+RL, a two-stage robust UDA framework that integrates Supervised Fine Tuning (SFT) and Reinforcement-inspired Learning (RL) on top of CLIP’s pre-trained visual encoder. In the SFT stage, we adversarially fine-tune a linear classifier using PGD-based perturbations over the labelled source domain while partially unfreezing CLIP’s projection layer. It allows adaptation to adversarial noise while preserving CLIP’s rich semantic priors. We introduce a confidence-guided pseudo-labeling strategy in the RL stage to annotate unlabeled target samples progressively. Pseudo labels are filtered using a decaying confidence threshold to balance quality and coverage, and the model is trained on a composite dataset formed by combining clean source samples with high-confidence target samples. Adversarial training is applied to mixed batches of clean and adversarial examples to enhance cross-domain robustness. Comprehensive evaluations on three benchmark datasets OfficeHome [18], PACS [7], and VisDA [13] demonstrate the effectiveness of our approach. Notably, SFT+RL achieves average improvements of 10.2% in clean accuracy and 15.8% in adversarial robustness across all three datasets, outperforming existing state-of-the-art methods.

Similar Papers
  • Conference Article
  • Citations31

Adversarial Robustness for Unsupervised Domain Adaptation

  • Oct 01, 2021
  • Muhammad Awais +6
  • 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
  • Citations2

Toward Improving Robustness and Accuracy in Unsupervised Domain Adaptation

  • Apr 11, 2025
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Aishwarya Soni +1
  • Conference Article
  • Citations4

Improving Robustness of Unsupervised Domain Adaptation with Adversarial Networks

  • Nov 28, 2023
  • Shuo Zhang +1
  • Book Chapter
  • Citations9

Exploring Adversarially Robust Training for Unsupervised Domain Adaptation

  • Jan 01, 2023
  • Shao-Yuan Lo +1
  • Research Article
  • Citations11

Revisiting the Trade-Off Between Accuracy and Robustness via Weight Distribution of Filters.

  • Dec 01, 2024
  • IEEE transactions on pattern analysis and machine intelligence
  • Xingxing Wei +2
  • Research Article
  • Citations26

Interpreting Adversarial Examples and Robustness for Deep Learning-Based Auto-Driving Systems

  • Jul 01, 2022
  • IEEE Transactions on Intelligent Transportation Systems
  • Ke Wang +5
  • PDF
  • Research Article
  • Citations9

LADDER: Latent boundary-guided adversarial training

  • Sep 09, 2022
  • Machine Learning
  • Xiaowei Zhou +2
  • 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
  • Citations121

Divergence-Agnostic Unsupervised Domain Adaptation by Adversarial Attacks.

  • Nov 01, 2022
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • Jingjing Li +5
  • Book Chapter
  • Citations22

Adversarial Examples in Deep Neural Networks: An Overview

  • Oct 24, 2019
  • Emilio Rafael Balda +2
  • Research Article
  • Citations12

Domain adaptive remote sensing image semantic segmentation with prototype guidance

  • Mar 06, 2024
  • Neurocomputing
  • Wankang Zeng +6
  • Research Article
  • Citations21

Adversarial robustness and attacks for multi-view deep models

  • Nov 12, 2020
  • Engineering Applications of Artificial Intelligence
  • Xuli Sun +1
  • PDF
  • Research Article
  • Citations31

Adversarial Robustness Enhancement for Deep Learning-Based Soft Sensors: An Adversarial Training Strategy Using Historical Gradients and Domain Adaptation.

  • Jun 17, 2024
  • Sensors (Basel, Switzerland)
  • Runyuan Guo +3
  • Research Article
  • Citations5

Provable Unrestricted Adversarial Training Without Compromise With Generalizability.

  • Dec 01, 2024
  • IEEE transactions on pattern analysis and machine intelligence
  • Lilin Zhang +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.