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 61–70 of 188 papers

Title	Date	Tasks	Status	Hype	Score
Contrastive Model Adaptation for Cross-Condition Robustness in Semantic Segmentation	Mar 9, 2023	Contrastive LearningDomain Adaptation	CodeCode Available	1	5
GALA: Graph Diffusion-based Alignment with Jigsaw for Source-free Domain Adaptation	Oct 22, 2024	Domain AdaptationGRAPH DOMAIN ADAPTATION	CodeCode Available	1	5
Shuffle PatchMix Augmentation with Confidence-Margin Weighted Pseudo-Labels for Enhanced Source-Free Domain Adaptation	May 30, 2025	Data AugmentationDomain Adaptation	CodeCode Available	0	5
Contrast and Clustering: Learning Neighborhood Pair Representation for Source-free Domain Adaptation	Jan 31, 2023	ClusteringContrastive Learning	CodeCode Available	0	5
SIDE: Self-supervised Intermediate Domain Exploration for Source-free Domain Adaptation	Oct 13, 2023	Domain AdaptationSelf-Supervised Learning	CodeCode Available	0	5
Few-shot Fine-tuning is All You Need for Source-free Domain Adaptation	Apr 3, 2023	AllDomain Adaptation	CodeCode Available	0	5
SFDA-rPPG: Source-Free Domain Adaptive Remote Physiological Measurement with Spatio-Temporal Consistency	Sep 18, 2024	Domain AdaptationDomain Generalization	CodeCode Available	0	5
SemEval-2021 Task 10: Source-Free Domain Adaptation for Semantic Processing	Aug 1, 2021	Domain AdaptationNegation	CodeCode Available	0	5
FACT: Federated Adversarial Cross Training	Jun 1, 2023	Domain AdaptationFederated Learning	CodeCode Available	0	5
Rethinking the Role of Pre-Trained Networks in Source-Free Domain Adaptation	Dec 15, 2022	Domain AdaptationRepresentation Learning	CodeCode Available	0	5

Show:10 25 50

← PrevPage 7 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