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

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 51–100 of 188 papers

TitleStatusHype
Exploiting the Intrinsic Neighborhood Structure for Source-free Domain AdaptationCode1
Universal Source-Free Domain AdaptationCode1
Source-free Domain Adaptation via Avatar Prototype Generation and AdaptationCode1
Cal-SFDA: Source-Free Domain-adaptive Semantic Segmentation with Differentiable Expected Calibration ErrorCode1
Cluster-level pseudo-labelling for source-free cross-domain facial expression recognitionCode1
Tent: Fully Test-time Adaptation by Entropy MinimizationCode1
GALA: Graph Diffusion-based Alignment with Jigsaw for Source-free Domain AdaptationCode1
Uncertainty-guided Source-free Domain AdaptationCode1
Generalized Source-free Domain AdaptationCode1
Concurrent Subsidiary Supervision for Unsupervised Source-Free Domain AdaptationCode1
Confident Anchor-Induced Multi-Source Free Domain AdaptationCode1
Source-Free Domain Adaptation for Medical Image Segmentation via Prototype-Anchored Feature Alignment and Contrastive LearningCode1
Efficient Source-Free Time-Series Adaptation via Parameter Subspace Disentanglement—0
A Chebyshev Confidence Guided Source-Free Domain Adaptation Framework for Medical Image Segmentation—0
A Comparison of Strategies for Source-Free Domain Adaptation—0
A Comprehensive Survey on Source-free Domain Adaptation—0
Active Source Free Domain Adaptation—0
Adaptive Adversarial Network for Source-Free Domain Adaptation—0
Aligning Non-Causal Factors for Transformer-Based Source-Free Domain Adaptation—0
Annotator: A Generic Active Learning Baseline for LiDAR Semantic Segmentation—0
Better Practices for Domain Adaptation—0
Black-box Source-free Domain Adaptation via Two-stage Knowledge Distillation—0
BLCUFIGHT at SemEval-2021 Task 10: Novel Unsupervised Frameworks For Source-Free Domain Adaptation—0
Cleaning Noisy Labels by Negative Ensemble Learning for Source-Free Unsupervised Domain Adaptation—0
Consistency Regularization for Generalizable Source-free Domain Adaptation—0
Day-Night Adaptation: An Innovative Source-free Adaptation Framework for Medical Image Segmentation—0
Discriminative Pattern Calibration Mechanism for Source-Free Domain Adaptation—0
Domain-Specificity Inducing Transformers for Source-Free Domain Adaptation—0
Dual Moving Average Pseudo-Labeling for Source-Free Inductive Domain Adaptation—0
ElimPCL: Eliminating Noise Accumulation with Progressive Curriculum Labeling for Source-Free Domain Adaptation—0
Evidentially Calibrated Source-Free Time-Series Domain Adaptation with Temporal Imputation—0
Exploiting Negative Learning for Implicit Pseudo Label Rectification in Source-Free Domain Adaptive Semantic Segmentation—0
Exploring Domain-Invariant Parameters for Source Free Domain Adaptation—0
Federated Source-free Domain Adaptation for Classification: Weighted Cluster Aggregation for Unlabeled Data—0
Feed-Forward Source-Free Domain Adaptation via Class Prototypes—0
Feed-Forward Latent Domain Adaptation—0
FREST: Feature RESToration for Semantic Segmentation under Multiple Adverse Conditions—0
Fuzzy-aware Loss for Source-free Domain Adaptation in Visual Emotion Recognition—0
Generating Reliable Pixel-Level Labels for Source Free Domain Adaptation—0
Generation, augmentation, and alignment: A pseudo-source domain based method for source-free domain adaptation—0
IITK at SemEval-2021 Task 10: Source-Free Unsupervised Domain Adaptation using Class Prototypes—0
Imbalance-Agnostic Source-Free Domain Adaptation via Avatar Prototype Alignment—0
Improving Online Source-free Domain Adaptation for Object Detection by Unsupervised Data Acquisition—0
In Search for a Generalizable Method for Source Free Domain Adaptation—0
Jacobian Norm for Unsupervised Source-Free Domain Adaptation—0
Knowledge-Data Fusion Based Source-Free Semi-Supervised Domain Adaptation for Seizure Subtype Classification—0
Label Calibration in Source Free Domain Adaptation—0
Learning Compositional Transferability of Time Series for Source-Free Domain Adaptation—0
Local-Global Pseudo-label Correction for Source-free Domain Adaptive Medical Image Segmentation—0
Low Saturation Confidence Distribution-based Test-Time Adaptation for Cross-Domain Remote Sensing Image Classification—0
Show:102550
← PrevPage 2 of 4Next →
All datasetsVisDA-2017PACSCityscapes to ACDCCityscapes to Dark Zurich

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1RCLAccuracy93.2—Unverified
2SFDA2++Accuracy89.6—Unverified
3SPMAccuracy89.4—Unverified
4SFDA2Accuracy88.1—Unverified
5C-SFDAAccuracy87.8—Unverified
6DaCAccuracy87.3—Unverified
7SHOT++Accuracy87.3—Unverified
8NRCAccuracy85.9—Unverified
9G-SFDAAccuracy85.4—Unverified
10SHOTAccuracy82.9—Unverified
#ModelMetricClaimedVerifiedStatus
1SPMAverage Accuracy86.7—Unverified
2DRAAverage Accuracy84—Unverified
3NELAverage Accuracy72.4—Unverified
#ModelMetricClaimedVerifiedStatus
1CMAmIoU69.1—Unverified
#ModelMetricClaimedVerifiedStatus
1CMAmIoU53.6—Unverified