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 150 of 188 papers

TitleStatusHype
Unified Source-Free Domain AdaptationCode3
A Comprehensive Survey on Test-Time Adaptation under Distribution ShiftsCode3
Proxy Denoising for Source-Free Domain AdaptationCode3
Source-Free Domain Adaptation for YOLO Object DetectionCode2
Source-Free Domain Adaptation with Frozen Multimodal Foundation ModelCode2
Source-free Domain Adaptation via Avatar Prototype Generation and AdaptationCode1
Source-free domain adaptation based on label reliability for cross-domain bearing fault diagnosisCode1
Source-Free Domain Adaptation for Medical Image Segmentation via Prototype-Anchored Feature Alignment and Contrastive LearningCode1
Simplifying Source-Free Domain Adaptation for Object Detection: Effective Self-Training Strategies and Performance InsightsCode1
SS-SFDA : Self-Supervised Source-Free Domain Adaptation for Road Segmentation in Hazardous EnvironmentsCode1
Source-Free Adaptation to Measurement Shift via Bottom-Up Feature RestorationCode1
Source-Free Domain Adaptation for Image SegmentationCode1
Generalized Source-free Domain AdaptationCode1
An Uncertainty-guided Tiered Self-training Framework for Active Source-free Domain Adaptation in Prostate SegmentationCode1
Uncertainty-Aware Source-Free Adaptive Image Super-Resolution with Wavelet Augmentation TransformerCode1
ProSFDA: Prompt Learning based Source-free Domain Adaptation for Medical Image SegmentationCode1
Instance Relation Graph Guided Source-Free Domain Adaptive Object DetectionCode1
Learning Across Domains and Devices: Style-Driven Source-Free Domain Adaptation in Clustered Federated LearningCode1
BMD: A General Class-balanced Multicentric Dynamic Prototype Strategy for Source-free Domain AdaptationCode1
Robust Source-Free Domain Adaptation for Fundus Image SegmentationCode1
SF(DA)^2: Source-free Domain Adaptation Through the Lens of Data AugmentationCode1
Sign Segmentation with Changepoint-Modulated Pseudo-LabellingCode1
Cluster-level pseudo-labelling for source-free cross-domain facial expression recognitionCode1
Source-Free Adaptive Gaze Estimation by Uncertainty ReductionCode1
Anatomy-guided domain adaptation for 3D in-bed human pose estimationCode1
Concurrent Subsidiary Supervision for Unsupervised Source-Free Domain AdaptationCode1
Guiding Pseudo-labels with Uncertainty Estimation for Source-free Unsupervised Domain AdaptationCode1
Confident Anchor-Induced Multi-Source Free Domain AdaptationCode1
C-SFDA: A Curriculum Learning Aided Self-Training Framework for Efficient Source Free Domain AdaptationCode1
Contrastive Model Adaptation for Cross-Condition Robustness in Semantic SegmentationCode1
CoSDA: Continual Source-Free Domain AdaptationCode1
Balancing Discriminability and Transferability for Source-Free Domain AdaptationCode1
Exploiting the Intrinsic Neighborhood Structure for Source-free Domain AdaptationCode1
GLC++: Source-Free Universal Domain Adaptation through Global-Local Clustering and Contrastive Affinity LearningCode1
Hyperbolic Active Learning for Semantic Segmentation under Domain ShiftCode1
DG-TTA: Out-of-domain Medical Image Segmentation through Augmentation and Descriptor-driven Domain Generalization and Test-Time AdaptationCode1
Source-free Video Domain Adaptation by Learning Temporal Consistency for Action RecognitionCode1
Attracting and Dispersing: A Simple Approach for Source-free Domain AdaptationCode1
Divide and Adapt: Active Domain Adaptation via Customized LearningCode1
Divide and Contrast: Source-free Domain Adaptation via Adaptive Contrastive LearningCode1
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 1 of 4Next →

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