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 125 of 188 papers

TitleStatusHype
Proxy Denoising for Source-Free Domain AdaptationCode3
Unified Source-Free Domain AdaptationCode3
A Comprehensive Survey on Test-Time Adaptation under Distribution ShiftsCode3
Source-Free Domain Adaptation for YOLO Object DetectionCode2
Source-Free Domain Adaptation with Frozen Multimodal Foundation ModelCode2
Source-free domain adaptation based on label reliability for cross-domain bearing fault diagnosisCode1
AIF-SFDA: Autonomous Information Filter-driven Source-Free Domain Adaptation for Medical Image SegmentationCode1
GALA: Graph Diffusion-based Alignment with Jigsaw for Source-free Domain AdaptationCode1
Train Till You Drop: Towards Stable and Robust Source-free Unsupervised 3D Domain AdaptationCode1
Dynamic Retraining-Updating Mean Teacher for Source-Free Object DetectionCode1
Simplifying Source-Free Domain Adaptation for Object Detection: Effective Self-Training Strategies and Performance InsightsCode1
An Uncertainty-guided Tiered Self-training Framework for Active Source-free Domain Adaptation in Prostate SegmentationCode1
GLC++: Source-Free Universal Domain Adaptation through Global-Local Clustering and Contrastive Affinity LearningCode1
SF(DA)^2: Source-free Domain Adaptation Through the Lens of Data AugmentationCode1
DG-TTA: Out-of-domain Medical Image Segmentation through Augmentation and Descriptor-driven Domain Generalization and Test-Time AdaptationCode1
Robust Source-Free Domain Adaptation for Fundus Image SegmentationCode1
UPL-SFDA: Uncertainty-aware Pseudo Label Guided Source-Free Domain Adaptation for Medical Image SegmentationCode1
Cal-SFDA: Source-Free Domain-adaptive Semantic Segmentation with Differentiable Expected Calibration ErrorCode1
ReCLIP: Refine Contrastive Language Image Pre-Training with Source Free Domain AdaptationCode1
Divide and Adapt: Active Domain Adaptation via Customized LearningCode1
Source-Free Domain Adaptation for Medical Image Segmentation via Prototype-Anchored Feature Alignment and Contrastive LearningCode1
Source-Free Domain Adaptation with Temporal Imputation for Time Series DataCode1
Source-Free Domain Adaptive Fundus Image Segmentation with Class-Balanced Mean TeacherCode1
Hyperbolic Active Learning for Semantic Segmentation under Domain ShiftCode1
Towards Source-free Domain Adaptive Semantic Segmentation via Importance-aware and Prototype-contrast LearningCode1
Show:102550
← PrevPage 1 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