# DRIVE: Dual-Robustness via Information Variability and Entropic Consistency in Source-Free Unsupervised Domain Adaptation

arXiv: https://arxiv.org/abs/2411.15976 · HTML: https://mlsanity.com/paper/2411.15976/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 36 references that are in the map.
- First posted on arXiv 24 Nov 2024.

## Builds on (most cited first, 26 of 26)

- [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)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Moment Matching for Multi-Source Domain Adaptation](https://mlsanity.com/paper/1812.01754/) (2018)
- [Deep Hashing Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1706.07522/) (2017)
- [Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2002.08546/) (2020)
- [Contrastive Adaptation Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1901.00976/) (2019)
- [LIV: Language-Image Representations and Rewards for Robotic Control](https://mlsanity.com/paper/2306.00958/) (2023)
- [Exploiting the Intrinsic Neighborhood Structure for Source-free Domain Adaptation](https://mlsanity.com/paper/2110.04202/) (2021)
- [Generalized Source-free Domain Adaptation](https://mlsanity.com/paper/2108.01614/) (2021)
- [Domain Adaptation via Prompt Learning](https://mlsanity.com/paper/2202.06687/) (2022)
- [Source-free Domain Adaptation via Avatar Prototype Generation and Adaptation](https://mlsanity.com/paper/2106.15326/) (2021)
- [A Comprehensive Survey on Source-free Domain Adaptation](https://mlsanity.com/paper/2302.11803/) (2023)
- [Source-Free Domain Adaptation via Distribution Estimation](https://mlsanity.com/paper/2204.11257/) (2022)
- [Attracting and Dispersing: A Simple Approach for Source-free Domain Adaptation](https://mlsanity.com/paper/2205.04183/) (2022)
- [Source-Free Unsupervised Domain Adaptation: A Survey](https://mlsanity.com/paper/2301.00265/) (2022)
- [VDM-DA: Virtual Domain Modeling for Source Data-free Domain Adaptation](https://mlsanity.com/paper/2103.14357/) (2021)
- [Guiding Pseudo-labels with Uncertainty Estimation for Source-free Unsupervised Domain Adaptation](https://mlsanity.com/paper/2303.03770/) (2023)
- [AD-CLIP: Adapting Domains in Prompt Space Using CLIP](https://mlsanity.com/paper/2308.05659/) (2023)
- [Confidence Score for Source-Free Unsupervised Domain Adaptation](https://mlsanity.com/paper/2206.06640/) (2022)
- [Balancing Discriminability and Transferability for Source-Free Domain Adaptation](https://mlsanity.com/paper/2206.08009/) (2022)
- [Source-Free Domain Adaptation with Frozen Multimodal Foundation Model](https://mlsanity.com/paper/2311.16510/) (2023)
- [Mutual Information Divergence: A Unified Metric for Multimodal Generative Models](https://mlsanity.com/paper/2205.13445/) (2022)
- [Hypothesis Disparity Regularized Mutual Information Maximization](https://mlsanity.com/paper/2012.08072/) (2020)
- [Enhancing and Adapting in the Clinic: Source-free Unsupervised Domain Adaptation for Medical Image Enhancement](https://mlsanity.com/paper/2312.01338/) (2023)
- [Source-free Domain Adaptive Object Detection in Remote Sensing Images](https://mlsanity.com/paper/2401.17916/) (2024)

## Abstract (arXiv)

Adapting machine learning models to new domains without labeled data, especially when source data is inaccessible, is a critical challenge in applications like medical imaging, autonomous driving, and remote sensing. This task, known as Source-Free Unsupervised Domain Adaptation (SFUDA), involves adapting a pre-trained model to a target domain using only unlabeled target data, which can lead to issues such as overfitting, underfitting, and poor generalization due to domain discrepancies and noise. Existing SFUDA methods often rely on single-model architectures, struggling with uncertainty and variability in the target domain. To address these challenges, we propose DRIVE (Dual-Robustness through Information Variability and Entropy), a novel SFUDA framework leveraging a dual-model architecture. The two models, initialized with identical weights, work in parallel to capture diverse target domain characteristics. One model is exposed to perturbations via projection gradient descent (PGD) guided by mutual information, focusing on high-uncertainty regions. We also introduce an entropy-aware pseudo-labeling strategy that adjusts label weights based on prediction uncertainty, ensuring the model focuses on reliable data while avoiding noisy regions. The adaptation process has two stages: the first aligns the models on stable features using a mutual information consistency loss, and the second dynamically adjusts the perturbation level based on the loss from the first stage, encouraging the model to explore a broader range of the target domain while preserving existing performance. This enhances generalization capabilities and robustness against interference. Evaluations on standard SFUDA benchmarks show that DRIVE consistently outperforms previous methods, delivering improved adaptation accuracy and stability across complex target domains.