Saved in:
Bibliographic Details
Main Authors: Karatsiolis, Savvas, Kamilaris, Andreas
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.16124
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908498815614976
author Karatsiolis, Savvas
Kamilaris, Andreas
author_facet Karatsiolis, Savvas
Kamilaris, Andreas
contents We propose Domain Adaptation via Feature Refinement (DAFR2), a simple yet effective framework for unsupervised domain adaptation under distribution shift. The proposed method synergistically combines three key components: adaptation of Batch Normalization statistics using unlabeled target data, feature distillation from a source-trained model and hypothesis transfer. By aligning feature distributions at the statistical and representational levels, DAFR2 produces robust and domain-invariant feature spaces that generalize across similar domains without requiring target labels, complex architectures or sophisticated training objectives. Extensive experiments on benchmark datasets, including CIFAR10-C, CIFAR100-C, MNIST-C and PatchCamelyon-C, demonstrate that the proposed algorithm outperforms prior methods in robustness to corruption. Theoretical and empirical analyses further reveal that our method achieves improved feature alignment, increased mutual information between the domains and reduced sensitivity to input perturbations.
format Preprint
id arxiv_https___arxiv_org_abs_2508_16124
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Domain Adaptation via Feature Refinement
Karatsiolis, Savvas
Kamilaris, Andreas
Computer Vision and Pattern Recognition
Machine Learning
We propose Domain Adaptation via Feature Refinement (DAFR2), a simple yet effective framework for unsupervised domain adaptation under distribution shift. The proposed method synergistically combines three key components: adaptation of Batch Normalization statistics using unlabeled target data, feature distillation from a source-trained model and hypothesis transfer. By aligning feature distributions at the statistical and representational levels, DAFR2 produces robust and domain-invariant feature spaces that generalize across similar domains without requiring target labels, complex architectures or sophisticated training objectives. Extensive experiments on benchmark datasets, including CIFAR10-C, CIFAR100-C, MNIST-C and PatchCamelyon-C, demonstrate that the proposed algorithm outperforms prior methods in robustness to corruption. Theoretical and empirical analyses further reveal that our method achieves improved feature alignment, increased mutual information between the domains and reduced sensitivity to input perturbations.
title Domain Adaptation via Feature Refinement
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2508.16124