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 151–160 of 188 papers

Title	Date	Tasks	Status
Dual Moving Average Pseudo-Labeling for Source-Free Inductive Domain Adaptation	Dec 15, 2022	Domain AdaptationSource-Free Domain Adaptation	—Unverified
Rethinking the Role of Pre-Trained Networks in Source-Free Domain Adaptation	Dec 15, 2022	Domain AdaptationRepresentation Learning	CodeCode Available
Self-training via Metric Learning for Source-Free Domain Adaptation of Semantic Segmentation	Dec 8, 2022	Domain AdaptationMetric Learning	—Unverified
Reconciling a Centroid-Hypothesis Conflict in Source-Free Domain Adaptation	Dec 7, 2022	Domain AdaptationPseudo Label	CodeCode Available
Variational Model Perturbation for Source-Free Domain Adaptation	Oct 19, 2022	Bayesian InferenceDomain Adaptation	CodeCode Available
Polycentric Clustering and Structural Regularization for Source-free Unsupervised Domain Adaptation	Oct 14, 2022	ClusteringDomain Adaptation	CodeCode Available
RAIN: RegulArization on Input and Network for Black-Box Domain Adaptation	Aug 22, 2022	Data AugmentationDomain Adaptation	CodeCode Available
Feed-Forward Latent Domain Adaptation	Jul 15, 2022	Domain AdaptationSource-Free Domain Adaptation	—Unverified
Source-Free Domain Adaptation for Real-world Image Dehazing	Jul 14, 2022	Domain AdaptationImage Dehazing	—Unverified
Test-Time Adaptation for Visual Document Understanding	Jun 15, 2022	document understandingDomain Adaptation	—Unverified

Show:10 25 50

← PrevPage 16 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