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

Showing 8190 of 188 papers

TitleStatusHype
Semantic Image Segmentation: Two Decades of Research0
SepRep-Net: Multi-source Free Domain Adaptation via Model Separation And Reparameterization0
Efficient Source-Free Time-Series Adaptation via Parameter Subspace Disentanglement0
Cleaning Noisy Labels by Negative Ensemble Learning for Source-Free Unsupervised Domain Adaptation0
Multi-Granularity Class Prototype Topology Distillation for Class-Incremental Source-Free Unsupervised Domain Adaptation0
MTLoc: A Confidence-Based Source-Free Domain Adaptation Approach For Indoor Localization0
MHPL: Minimum Happy Points Learning for Active Source Free Domain Adaptation0
Dual Moving Average Pseudo-Labeling for Source-Free Inductive Domain Adaptation0
Revisiting Source-Free Domain Adaptation: Insights into Representativeness, Generalization, and Variety0
MedAI at SemEval-2021 Task 10: Negation-aware Pre-training for Source-free Negation Detection Domain Adaptation0
Show:102550
← PrevPage 9 of 19Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1RCLAccuracy93.2Unverified
2SFDA2++Accuracy89.6Unverified
3SPMAccuracy89.4Unverified
4SFDA2Accuracy88.1Unverified
5C-SFDAAccuracy87.8Unverified
6DaCAccuracy87.3Unverified
7SHOT++Accuracy87.3Unverified
8NRCAccuracy85.9Unverified
9G-SFDAAccuracy85.4Unverified
10SHOTAccuracy82.9Unverified
#ModelMetricClaimedVerifiedStatus
1SPMAverage Accuracy86.7Unverified
2DRAAverage Accuracy84Unverified
3NELAverage Accuracy72.4Unverified
#ModelMetricClaimedVerifiedStatus
1CMAmIoU69.1Unverified
#ModelMetricClaimedVerifiedStatus
1CMAmIoU53.6Unverified