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 131140 of 188 papers

TitleStatusHype
Plug-and-play Shape Refinement Framework for Multi-site and Lifespan Brain Skull Stripping0
Unsupervised Adaptation of Polyp Segmentation Models via Coarse-to-Fine Self-Supervision0
Source-Free Domain Adaptation for Real-world Image Dehazing0
Source-Free Domain Adaptation for RGB-D Semantic Segmentation with Vision Transformers0
Source-Free Domain Adaptation for Semantic Segmentation0
Source -Free Domain Adaptation for Speaker Verification in Data-Scarce Languages and Noisy Channels0
Source-free Domain Adaptation for Video Object Detection Under Adverse Image Conditions0
Dual Moving Average Pseudo-Labeling for Source-Free Inductive Domain Adaptation0
Unsupervised Domain Adaptation for Semantic Image Segmentation: a Comprehensive Survey0
A Comprehensive Survey on Source-free Domain Adaptation0
Show:102550
← PrevPage 14 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