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 81–90 of 188 papers

Title	Date	Tasks	Status	Hype
ReCLIP: Refine Contrastive Language Image Pre-Training with Source Free Domain Adaptation	Aug 4, 2023	Domain Adaptationimage-classification	CodeCode Available	1
Consistency Regularization for Generalizable Source-free Domain Adaptation	Aug 3, 2023	Domain AdaptationPseudo Label	—Unverified	0
Divide and Adapt: Active Domain Adaptation via Customized Learning	Jul 21, 2023	Active LearningDomain Adaptation	CodeCode Available	1
Feed-Forward Source-Free Domain Adaptation via Class Prototypes	Jul 20, 2023	Domain AdaptationSource-Free Domain Adaptation	—Unverified	0
Source-Free Domain Adaptation for Medical Image Segmentation via Prototype-Anchored Feature Alignment and Contrastive Learning	Jul 19, 2023	Contrastive LearningDomain Adaptation	CodeCode Available	1
Unsupervised Accuracy Estimation of Deep Visual Models using Domain-Adaptive Adversarial Perturbation without Source Samples	Jul 19, 2023	Domain AdaptationSource-Free Domain Adaptation	—Unverified	0
Source-Free Domain Adaptive Fundus Image Segmentation with Class-Balanced Mean Teacher	Jul 14, 2023	Image SegmentationSemantic Segmentation	CodeCode Available	1
Source-Free Domain Adaptation with Temporal Imputation for Time Series Data	Jul 14, 2023	Domain AdaptationImputation	CodeCode Available	1
Generating Reliable Pixel-Level Labels for Source Free Domain Adaptation	Jul 3, 2023	Domain AdaptationImage-to-Image Translation	—Unverified	0
Learning Content-enhanced Mask Transformer for Domain Generalized Urban-Scene Segmentation	Jul 1, 2023	DecoderDomain Adaptation	CodeCode Available	0

Show:10 25 50

← PrevPage 9 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