SOTAVerified

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 AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 151–175 of 188 papers

TitleStatusHype
Dual Moving Average Pseudo-Labeling for Source-Free Inductive Domain Adaptation—0
Rethinking the Role of Pre-Trained Networks in Source-Free Domain AdaptationCode0
Self-training via Metric Learning for Source-Free Domain Adaptation of Semantic Segmentation—0
Reconciling a Centroid-Hypothesis Conflict in Source-Free Domain AdaptationCode0
Variational Model Perturbation for Source-Free Domain AdaptationCode0
Polycentric Clustering and Structural Regularization for Source-free Unsupervised Domain AdaptationCode0
RAIN: RegulArization on Input and Network for Black-Box Domain AdaptationCode0
Feed-Forward Latent Domain Adaptation—0
Source-Free Domain Adaptation for Real-world Image Dehazing—0
Test-Time Adaptation for Visual Document Understanding—0
Active Source Free Domain Adaptation—0
A Comparison of Strategies for Source-Free Domain AdaptationCode0
Source-Free Domain Adaptation via Distribution EstimationCode0
Jacobian Norm for Unsupervised Source-Free Domain Adaptation—0
Plug-and-play Shape Refinement Framework for Multi-site and Lifespan Brain Skull Stripping—0
Cleaning Noisy Labels by Negative Ensemble Learning for Source-Free Unsupervised Domain Adaptation—0
On Balancing Bias and Variance in Unsupervised Multi-Source-Free Domain AdaptationCode0
Exploring Domain-Invariant Parameters for Source Free Domain Adaptation—0
Unsupervised Domain Adaptation for Semantic Image Segmentation: a Comprehensive Survey—0
Test-time Batch Statistics Calibration for Covariate Shift—0
Generation, augmentation, and alignment: A pseudo-source domain based method for source-free domain adaptation—0
A Comparison of Strategies for Source-Free Domain Adaptation—0
YNU-HPCC at SemEval-2021 Task 10: Using a Transformer-based Source-Free Domain Adaptation Model for Semantic Processing—0
IITK at SemEval-2021 Task 10: Source-Free Unsupervised Domain Adaptation using Class Prototypes—0
The University of Arizona at SemEval-2021 Task 10: Applying Self-training, Active Learning and Data Augmentation to Source-free Domain Adaptation—0
Show:102550
← PrevPage 7 of 8Next →
All datasetsVisDA-2017PACSCityscapes to ACDCCityscapes to Dark Zurich

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1RCLAccuracy93.2—Unverified
2SFDA2++Accuracy89.6—Unverified
3SPMAccuracy89.4—Unverified
4SFDA2Accuracy88.1—Unverified
5C-SFDAAccuracy87.8—Unverified
6DaCAccuracy87.3—Unverified
7SHOT++Accuracy87.3—Unverified
8NRCAccuracy85.9—Unverified
9G-SFDAAccuracy85.4—Unverified
10SHOTAccuracy82.9—Unverified
#ModelMetricClaimedVerifiedStatus
1SPMAverage Accuracy86.7—Unverified
2DRAAverage Accuracy84—Unverified
3NELAverage Accuracy72.4—Unverified
#ModelMetricClaimedVerifiedStatus
1CMAmIoU69.1—Unverified
#ModelMetricClaimedVerifiedStatus
1CMAmIoU53.6—Unverified