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 171–180 of 188 papers

Title	Date	Tasks	Status	Hype
Semi-Supervised Hypothesis Transfer for Source-Free Domain Adaptation	Jul 14, 2021	Domain AdaptationSource-Free Domain Adaptation	—Unverified	0
Uncertainty-Guided Mixup for Semi-Supervised Domain Adaptation without Source Data	Jul 14, 2021	Domain AdaptationPrivacy Preserving	—Unverified	0
Source-Free Adaptation to Measurement Shift via Bottom-Up Feature Restoration	Jul 12, 2021	Domain AdaptationSource-Free Domain Adaptation	CodeCode Available	1
Exploiting Negative Learning for Implicit Pseudo Label Rectification in Source-Free Domain Adaptive Semantic Segmentation	Jun 23, 2021	Domain AdaptationPseudo Label	—Unverified	0
A Curriculum-style Self-training Approach for Source-Free Semantic Segmentation	Jun 22, 2021	Domain AdaptationRepresentation Learning	CodeCode Available	0
Source-free Domain Adaptation via Avatar Prototype Generation and Adaptation	Jun 18, 2021	Contrastive LearningDomain Adaptation	CodeCode Available	1
Transformer-Based Source-Free Domain Adaptation	May 28, 2021	Domain AdaptationKnowledge Distillation	CodeCode Available	1
Sign Segmentation with Changepoint-Modulated Pseudo-Labelling	Apr 28, 2021	Domain AdaptationSegmentation	CodeCode Available	1
Source-Free Domain Adaptation for Semantic Segmentation	Mar 30, 2021	Domain AdaptationSegmentation	—Unverified	0
Source-free Domain Adaptation via Distributional Alignment by Matching Batch Normalization Statistics	Jan 19, 2021	Domain AdaptationSource-Free Domain Adaptation	—Unverified	0

Show:10 25 50

← PrevPage 18 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