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 41–50 of 188 papers

Title	Date	Tasks	Status	Hype	Score
GLC++: Source-Free Universal Domain Adaptation through Global-Local Clustering and Contrastive Affinity Learning	Mar 21, 2024	ClusteringContrastive Learning	CodeCode Available	1	5
Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation	Feb 20, 2020	Domain AdaptationPartial Domain Adaptation	CodeCode Available	1	5
Cal-SFDA: Source-Free Domain-adaptive Semantic Segmentation with Differentiable Expected Calibration Error	Aug 6, 2023	Domain AdaptationModel Selection	CodeCode Available	1	5
Dynamic Retraining-Updating Mean Teacher for Source-Free Object Detection	Jul 23, 2024	Domain Adaptationobject-detection	CodeCode Available	1	5
AIF-SFDA: Autonomous Information Filter-driven Source-Free Domain Adaptation for Medical Image Segmentation	Jan 6, 2025	Domain AdaptationImage Segmentation	CodeCode Available	1	5
Guiding Pseudo-labels with Uncertainty Estimation for Source-free Unsupervised Domain Adaptation	Mar 7, 2023	Domain AdaptationSource-Free Domain Adaptation	CodeCode Available	1	5
SS-SFDA : Self-Supervised Source-Free Domain Adaptation for Road Segmentation in Hazardous Environments	Nov 27, 2020	Autonomous VehiclesDomain Adaptation	CodeCode Available	1	5
Source-free Video Domain Adaptation by Learning Temporal Consistency for Action Recognition	Mar 9, 2022	Action RecognitionDomain Adaptation	CodeCode Available	1	5
Source-Free Adaptation to Measurement Shift via Bottom-Up Feature Restoration	Jul 12, 2021	Domain AdaptationSource-Free Domain Adaptation	CodeCode Available	1	5
Uncertainty-Aware Source-Free Adaptive Image Super-Resolution with Wavelet Augmentation Transformer	Mar 31, 2023	Domain AdaptationImage Super-Resolution	CodeCode Available	1	5

Show:10 25 50

← PrevPage 5 of 19Next →

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