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

TL;DR

DRIVE introduces a dual-model framework for source-free unsupervised domain adaptation, enhancing robustness and accuracy by leveraging information variability, entropy-aware pseudo-labeling, and dynamic perturbation strategies.

Contribution

The paper proposes a novel dual-model approach with entropy-aware pseudo-labeling and dynamic perturbation to improve SFUDA performance and robustness.

Findings

Outperforms previous SFUDA methods on standard benchmarks.

Enhances adaptation stability across complex target domains.

Improves generalization by exploring broader target domain features.

Abstract

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.