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 2650 of 188 papers

TitleStatusHype
CoSDA: Continual Source-Free Domain AdaptationCode1
Uncertainty-Aware Source-Free Adaptive Image Super-Resolution with Wavelet Augmentation TransformerCode1
C-SFDA: A Curriculum Learning Aided Self-Training Framework for Efficient Source Free Domain AdaptationCode1
SFHarmony: Source Free Domain Adaptation for Distributed Neuroimaging AnalysisCode1
Upcycling Models under Domain and Category ShiftCode1
Contrastive Model Adaptation for Cross-Condition Robustness in Semantic SegmentationCode1
Guiding Pseudo-labels with Uncertainty Estimation for Source-free Unsupervised Domain AdaptationCode1
Source-Free Adaptive Gaze Estimation by Uncertainty ReductionCode1
Towards Better Stability and Adaptability: Improve Online Self-Training for Model Adaptation in Semantic SegmentationCode1
Anatomy-guided domain adaptation for 3D in-bed human pose estimationCode1
ProSFDA: Prompt Learning based Source-free Domain Adaptation for Medical Image SegmentationCode1
Divide and Contrast: Source-free Domain Adaptation via Adaptive Contrastive LearningCode1
TTTFlow: Unsupervised Test-Time Training with Normalizing FlowCode1
Cluster-level pseudo-labelling for source-free cross-domain facial expression recognitionCode1
Learning Across Domains and Devices: Style-Driven Source-Free Domain Adaptation in Clustered Federated LearningCode1
Uncertainty-guided Source-free Domain AdaptationCode1
Concurrent Subsidiary Supervision for Unsupervised Source-Free Domain AdaptationCode1
Balancing Discriminability and Transferability for Source-Free Domain AdaptationCode1
ProxyMix: Proxy-based Mixup Training with Label Refinery for Source-Free Domain AdaptationCode1
Attracting and Dispersing: A Simple Approach for Source-free Domain AdaptationCode1
BMD: A General Class-balanced Multicentric Dynamic Prototype Strategy for Source-free Domain AdaptationCode1
Instance Relation Graph Guided Source-Free Domain Adaptive Object DetectionCode1
Source-free Video Domain Adaptation by Learning Temporal Consistency for Action RecognitionCode1
Confident Anchor-Induced Multi-Source Free Domain AdaptationCode1
Exploiting the Intrinsic Neighborhood Structure for Source-free Domain AdaptationCode1
Show:102550
← PrevPage 2 of 8Next →

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