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 2130 of 188 papers

TitleStatusHype
Semi-Supervised Transfer Boosting (SS-TrBoosting)0
Knowledge-Data Fusion Based Source-Free Semi-Supervised Domain Adaptation for Seizure Subtype Classification0
Multi-Granularity Class Prototype Topology Distillation for Class-Incremental Source-Free Unsupervised Domain Adaptation0
Unveiling the Superior Paradigm: A Comparative Study of Source-Free Domain Adaptation and Unsupervised Domain Adaptation0
Recall and Refine: A Simple but Effective Source-free Open-set Domain Adaptation FrameworkCode0
GALA: Graph Diffusion-based Alignment with Jigsaw for Source-free Domain AdaptationCode1
Day-Night Adaptation: An Innovative Source-free Adaptation Framework for Medical Image Segmentation0
Efficient Source-Free Time-Series Adaptation via Parameter Subspace Disentanglement0
A3: Active Adversarial Alignment for Source-Free Domain AdaptationCode0
Source-Free Domain Adaptation for YOLO Object DetectionCode2
Show:102550
← PrevPage 3 of 19Next →

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