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 101150 of 188 papers

TitleStatusHype
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
A Comprehensive Survey on Test-Time Adaptation under Distribution ShiftsCode3
Spatio-Temporal Pixel-Level Contrastive Learning-based Source-Free Domain Adaptation for Video Semantic SegmentationCode0
TempT: Temporal consistency for Test-time adaptation0
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
A Comprehensive Survey on Source-free Domain Adaptation0
In Search for a Generalizable Method for Source Free Domain Adaptation0
Semantic Image Segmentation: Two Decades of Research0
When Source-Free Domain Adaptation Meets Learning with Noisy Labels0
Contrast and Clustering: Learning Neighborhood Pair Representation for Source-free Domain AdaptationCode0
Chaos to Order: A Label Propagation Perspective on Source-Free Domain Adaptation0
1st Place Solution for ECCV 2022 OOD-CV Challenge Object Detection TrackCode0
SSDA: Secure Source-Free Domain AdaptationCode0
Source-Free Adaptive Gaze Estimation by Uncertainty ReductionCode1
MHPL: Minimum Happy Points Learning for Active Source Free Domain Adaptation0
Towards Better Stability and Adaptability: Improve Online Self-Training for Model Adaptation in Semantic SegmentationCode1
Source-Free Video Domain Adaptation With Spatial-Temporal-Historical Consistency Learning0
Source-Free Domain Adaptation for Question Answering with Masked Self-trainingCode0
Dual Moving Average Pseudo-Labeling for Source-Free Inductive Domain Adaptation0
Rethinking the Role of Pre-Trained Networks in Source-Free Domain AdaptationCode0
Self-training via Metric Learning for Source-Free Domain Adaptation of Semantic Segmentation0
Reconciling a Centroid-Hypothesis Conflict in Source-Free Domain AdaptationCode0
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
Variational Model Perturbation for Source-Free Domain AdaptationCode0
Polycentric Clustering and Structural Regularization for Source-free Unsupervised Domain AdaptationCode0
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
RAIN: RegulArization on Input and Network for Black-Box Domain AdaptationCode0
Uncertainty-guided Source-free Domain AdaptationCode1
Concurrent Subsidiary Supervision for Unsupervised Source-Free Domain AdaptationCode1
Feed-Forward Latent Domain Adaptation0
Source-Free Domain Adaptation for Real-world Image Dehazing0
Balancing Discriminability and Transferability for Source-Free Domain AdaptationCode1
Test-Time Adaptation for Visual Document Understanding0
ProxyMix: Proxy-based Mixup Training with Label Refinery for Source-Free Domain AdaptationCode1
Active Source Free Domain Adaptation0
Attracting and Dispersing: A Simple Approach for Source-free Domain AdaptationCode1
A Comparison of Strategies for Source-Free Domain AdaptationCode0
Source-Free Domain Adaptation via Distribution EstimationCode0
Jacobian Norm for Unsupervised Source-Free Domain Adaptation0
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
Show:102550
← PrevPage 3 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