Key Design Choices in Source-Free Unsupervised Domain Adaptation: An In-depth Empirical Analysis

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Maracani, Andrea, Camoriano, Raffaello, Maiettini, Elisa, Talon, Davide, Rosasco, Lorenzo, Natale, Lorenzo
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911783940259840
author Maracani, Andrea
Camoriano, Raffaello
Maiettini, Elisa
Talon, Davide
Rosasco, Lorenzo
Natale, Lorenzo
author_facet Maracani, Andrea
Camoriano, Raffaello
Maiettini, Elisa
Talon, Davide
Rosasco, Lorenzo
Natale, Lorenzo
contents This study provides a comprehensive benchmark framework for Source-Free Unsupervised Domain Adaptation (SF-UDA) in image classification, aiming to achieve a rigorous empirical understanding of the complex relationships between multiple key design factors in SF-UDA methods. The study empirically examines a diverse set of SF-UDA techniques, assessing their consistency across datasets, sensitivity to specific hyperparameters, and applicability across different families of backbone architectures. Moreover, it exhaustively evaluates pre-training datasets and strategies, particularly focusing on both supervised and self-supervised methods, as well as the impact of fine-tuning on the source domain. Our analysis also highlights gaps in existing benchmark practices, guiding SF-UDA research towards more effective and general approaches. It emphasizes the importance of backbone architecture and pre-training dataset selection on SF-UDA performance, serving as an essential reference and providing key insights. Lastly, we release the source code of our experimental framework. This facilitates the construction, training, and testing of SF-UDA methods, enabling systematic large-scale experimental analysis and supporting further research efforts in this field.
format Preprint
id arxiv_https___arxiv_org_abs_2402_16090
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Key Design Choices in Source-Free Unsupervised Domain Adaptation: An In-depth Empirical Analysis
Maracani, Andrea
Camoriano, Raffaello
Maiettini, Elisa
Talon, Davide
Rosasco, Lorenzo
Natale, Lorenzo
Computer Vision and Pattern Recognition
Machine Learning
This study provides a comprehensive benchmark framework for Source-Free Unsupervised Domain Adaptation (SF-UDA) in image classification, aiming to achieve a rigorous empirical understanding of the complex relationships between multiple key design factors in SF-UDA methods. The study empirically examines a diverse set of SF-UDA techniques, assessing their consistency across datasets, sensitivity to specific hyperparameters, and applicability across different families of backbone architectures. Moreover, it exhaustively evaluates pre-training datasets and strategies, particularly focusing on both supervised and self-supervised methods, as well as the impact of fine-tuning on the source domain. Our analysis also highlights gaps in existing benchmark practices, guiding SF-UDA research towards more effective and general approaches. It emphasizes the importance of backbone architecture and pre-training dataset selection on SF-UDA performance, serving as an essential reference and providing key insights. Lastly, we release the source code of our experimental framework. This facilitates the construction, training, and testing of SF-UDA methods, enabling systematic large-scale experimental analysis and supporting further research efforts in this field.
title Key Design Choices in Source-Free Unsupervised Domain Adaptation: An In-depth Empirical Analysis
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2402.16090