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 126–150 of 188 papers

Title	Date	Tasks	Status	Hype
Reconciling a Centroid-Hypothesis Conflict in Source-Free Domain Adaptation	Dec 7, 2022	Domain AdaptationPseudo Label	CodeCode Available	0
Anatomy-guided domain adaptation for 3D in-bed human pose estimation	Nov 22, 2022	3D Human Pose EstimationAnatomy	CodeCode Available	1
ProSFDA: Prompt Learning based Source-free Domain Adaptation for Medical Image Segmentation	Nov 21, 2022	Domain AdaptationImage Segmentation	CodeCode Available	1
Divide and Contrast: Source-free Domain Adaptation via Adaptive Contrastive Learning	Nov 12, 2022	Contrastive LearningDomain Adaptation	CodeCode Available	1
TTTFlow: Unsupervised Test-Time Training with Normalizing Flow	Oct 20, 2022	image-classificationImage Classification	CodeCode Available	1
Variational Model Perturbation for Source-Free Domain Adaptation	Oct 19, 2022	Bayesian InferenceDomain Adaptation	CodeCode Available	0
Polycentric Clustering and Structural Regularization for Source-free Unsupervised Domain Adaptation	Oct 14, 2022	ClusteringDomain Adaptation	CodeCode Available	0
Cluster-level pseudo-labelling for source-free cross-domain facial expression recognition	Oct 11, 2022	Cross-Domain Facial Expression RecognitionDomain Adaptation	CodeCode Available	1
Learning Across Domains and Devices: Style-Driven Source-Free Domain Adaptation in Clustered Federated Learning	Oct 5, 2022	Autonomous DrivingDomain Adaptation	CodeCode Available	1
RAIN: RegulArization on Input and Network for Black-Box Domain Adaptation	Aug 22, 2022	Data AugmentationDomain Adaptation	CodeCode Available	0
Uncertainty-guided Source-free Domain Adaptation	Aug 16, 2022	Domain AdaptationSource-Free Domain Adaptation	CodeCode Available	1
Concurrent Subsidiary Supervision for Unsupervised Source-Free Domain Adaptation	Jul 27, 2022	Domain AdaptationSource-Free Domain Adaptation	CodeCode Available	1
Feed-Forward Latent Domain Adaptation	Jul 15, 2022	Domain AdaptationSource-Free Domain Adaptation	—Unverified	0
Source-Free Domain Adaptation for Real-world Image Dehazing	Jul 14, 2022	Domain AdaptationImage Dehazing	—Unverified	0
Balancing Discriminability and Transferability for Source-Free Domain Adaptation	Jun 16, 2022	Domain AdaptationSemantic Segmentation	CodeCode Available	1
Test-Time Adaptation for Visual Document Understanding	Jun 15, 2022	document understandingDomain Adaptation	—Unverified	0
ProxyMix: Proxy-based Mixup Training with Label Refinery for Source-Free Domain Adaptation	May 29, 2022	Domain AdaptationObject Recognition	CodeCode Available	1
Active Source Free Domain Adaptation	May 22, 2022	Domain AdaptationSource-Free Domain Adaptation	—Unverified	0
Attracting and Dispersing: A Simple Approach for Source-free Domain Adaptation	May 9, 2022	ClusteringDiversity	CodeCode Available	1
A Comparison of Strategies for Source-Free Domain Adaptation	May 1, 2022	Active LearningData Augmentation	CodeCode Available	0
Source-Free Domain Adaptation via Distribution Estimation	Apr 24, 2022	Domain AdaptationPrivacy Preserving	CodeCode Available	0
Jacobian Norm for Unsupervised Source-Free Domain Adaptation	Apr 7, 2022	Domain AdaptationSource-Free Domain Adaptation	—Unverified	0
BMD: A General Class-balanced Multicentric Dynamic Prototype Strategy for Source-free Domain Adaptation	Apr 6, 2022	ClusteringDomain Adaptation	CodeCode Available	1
Instance Relation Graph Guided Source-Free Domain Adaptive Object Detection	Mar 29, 2022	Domain AdaptationKnowledge Distillation	CodeCode Available	1
Source-free Video Domain Adaptation by Learning Temporal Consistency for Action Recognition	Mar 9, 2022	Action RecognitionDomain Adaptation	CodeCode Available	1

Show:10 25 50

← PrevPage 6 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