Source-Free Domain Adaptation

Source-Free Domain Adaptation (SFDA) is a domain adaptation method in machine learning and computer vision where the goal is to adapt a pre-trained model to a new, target domain without access to the source domain data. This approach is advantageous in scenarios where sharing the source data is impractical due to privacy concerns, data size, or proprietary restrictions

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 176–188 of 188 papers

Title	Date	Tasks	Status
Physics-informed and Unsupervised Riemannian Domain Adaptation for Machine Learning on Heterogeneous EEG Datasets	Mar 7, 2024	Brain Computer Interfacechannel selection	—Unverified
Better Practices for Domain Adaptation	Sep 7, 2023	BenchmarkingDomain Adaptation	—Unverified
Prior-guided Source-free Domain Adaptation for Human Pose Estimation	Aug 26, 2023	2D Human Pose EstimationDomain Adaptation	—Unverified
Probability Distribution Alignment and Low-Rank Weight Decomposition for Source-Free Domain Adaptive Brain Decoding	Apr 12, 2025	Brain DecodingDomain Adaptation	—Unverified
Jacobian Norm for Unsupervised Source-Free Domain Adaptation	Apr 7, 2022	Domain AdaptationSource-Free Domain Adaptation	—Unverified
Trust your Good Friends: Source-free Domain Adaptation by Reciprocal Neighborhood Clustering	Sep 1, 2023	ClusteringDomain Adaptation	—Unverified
In Search for a Generalizable Method for Source Free Domain Adaptation	Feb 13, 2023	Domain AdaptationSource-Free Domain Adaptation	—Unverified
Improving Online Source-free Domain Adaptation for Object Detection by Unsupervised Data Acquisition	Oct 30, 2023	Autonomous VehiclesDomain Adaptation	—Unverified
Annotator: A Generic Active Learning Baseline for LiDAR Semantic Segmentation	Oct 31, 2023	Active LearningDomain Adaptation	—Unverified
Imbalance-Agnostic Source-Free Domain Adaptation via Avatar Prototype Alignment	May 22, 2023	Domain AdaptationPseudo Label	—Unverified
Uncertainty-Guided Mixup for Semi-Supervised Domain Adaptation without Source Data	Jul 14, 2021	Domain AdaptationPrivacy Preserving	—Unverified
Revisiting Source-Free Domain Adaptation: Insights into Representativeness, Generalization, and Variety	Jan 1, 2025	Domain AdaptationSource-Free Domain Adaptation	—Unverified
IITK at SemEval-2021 Task 10: Source-Free Unsupervised Domain Adaptation using Class Prototypes	Aug 1, 2021	Data AugmentationDomain Adaptation	—Unverified

Show:10 25 50

← PrevPage 8 of 8Next →

All datasets VisDA-2017 PACS Cityscapes to ACDC Cityscapes to Dark Zurich

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	RCL	Accuracy	93.2	—	Unverified
2	SFDA2++	Accuracy	89.6	—	Unverified
3	SPM	Accuracy	89.4	—	Unverified
4	SFDA2	Accuracy	88.1	—	Unverified
5	C-SFDA	Accuracy	87.8	—	Unverified
6	DaC	Accuracy	87.3	—	Unverified
7	SHOT++	Accuracy	87.3	—	Unverified
8	NRC	Accuracy	85.9	—	Unverified
9	G-SFDA	Accuracy	85.4	—	Unverified
10	SHOT	Accuracy	82.9	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	SPM	Average Accuracy	86.7	—	Unverified
2	DRA	Average Accuracy	84	—	Unverified
3	NEL	Average Accuracy	72.4	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	CMA	mIoU	69.1	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	CMA	mIoU	53.6	—	Unverified