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

arXiv: https://arxiv.org/abs/2607.03600 · HTML: https://mlsanity.com/paper/2607.03600/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Adversarial robustness and RL in finance, one of 15 directions in Deep reinforcement learning methods.
- Builds on 19 of its 23 references that are in the map.
- First posted on arXiv 3 Jul 2026.

## Placed in

- Deep reinforcement learning methods / [Adversarial robustness and RL in finance](https://mlsanity.com/deeprl/adversarial-robustness-and-rl-in-finance/)

## Builds on (most cited first, 19 of 19)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Theoretically Principled Trade-off between Robustness and Accuracy](https://mlsanity.com/paper/1901.08573/) (2019)
- [WILDS: A Benchmark of in-the-Wild Distribution Shifts](https://mlsanity.com/paper/2012.07421/) (2020)
- [Deep Hashing Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1706.07522/) (2017)
- [Deeper, Broader and Artier Domain Generalization](https://mlsanity.com/paper/1710.03077/) (2017)
- [Learning to Generalize: Meta-Learning for Domain Generalization](https://mlsanity.com/paper/1710.03463/) (2017)
- [Deep Visual Domain Adaptation: A Survey](https://mlsanity.com/paper/1802.03601/) (2018)
- [VisDA: The Visual Domain Adaptation Challenge](https://mlsanity.com/paper/1710.06924/) (2017)
- [Contrastive Adaptation Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1901.00976/) (2019)
- [Semi-supervised Domain Adaptation via Minimax Entropy](https://mlsanity.com/paper/1904.06487/) (2019)
- [Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models](https://mlsanity.com/paper/2402.12336/) (2024)
- [Exploring Architectural Ingredients of Adversarially Robust Deep Neural Networks](https://mlsanity.com/paper/2110.03825/) (2021)
- [An Adversarial Perturbation Oriented Domain Adaptation Approach for Semantic Segmentation](https://mlsanity.com/paper/1912.08954/) (2019)
- [Transferable, Controllable, and Inconspicuous Adversarial Attacks on Person Re-identification With Deep Mis-Ranking](https://mlsanity.com/paper/2004.04199/) (2020)
- [Exploring Adversarially Robust Training for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2202.09300/) (2022)
- [SRoUDA: Meta Self-training for Robust Unsupervised Domain Adaptation](https://mlsanity.com/paper/2212.05917/) (2022)
- [DART: A Principled Approach to Adversarially Robust Unsupervised Domain Adaptation](https://mlsanity.com/paper/2402.11120/) (2024)

## Abstract (arXiv)

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 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~citetomm-ude, PACS~citepacs, and VisDA~citevisda 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.