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 4150 of 188 papers

TitleStatusHype
ReCLIP: Refine Contrastive Language Image Pre-Training with Source Free Domain AdaptationCode1
Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain AdaptationCode1
Cal-SFDA: Source-Free Domain-adaptive Semantic Segmentation with Differentiable Expected Calibration ErrorCode1
Dynamic Retraining-Updating Mean Teacher for Source-Free Object DetectionCode1
AIF-SFDA: Autonomous Information Filter-driven Source-Free Domain Adaptation for Medical Image SegmentationCode1
SFHarmony: Source Free Domain Adaptation for Distributed Neuroimaging AnalysisCode1
ProxyMix: Proxy-based Mixup Training with Label Refinery for Source-Free Domain AdaptationCode1
GALA: Graph Diffusion-based Alignment with Jigsaw for Source-free Domain AdaptationCode1
Tent: Fully Test-time Adaptation by Entropy MinimizationCode1
Source Data-absent Unsupervised Domain Adaptation through Hypothesis Transfer and Labeling TransferCode1
Show:102550
← PrevPage 5 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