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 141150 of 188 papers

TitleStatusHype
Unveiling the Superior Paradigm: A Comparative Study of Source-Free Domain Adaptation and Unsupervised Domain Adaptation0
Source-free Domain Adaptation Requires Penalized Diversity0
YNU-HPCC at SemEval-2021 Task 10: Using a Transformer-based Source-Free Domain Adaptation Model for Semantic Processing0
Source-free Domain Adaptation via Distributional Alignment by Matching Batch Normalization Statistics0
Domain-Specificity Inducing Transformers for Source-Free Domain Adaptation0
Source-Free Domain Adaptation with Diffusion-Guided Source Data Generation0
Discriminative Pattern Calibration Mechanism for Source-Free Domain Adaptation0
Source Free Domain Adaptation with Image Translation0
Day-Night Adaptation: An Innovative Source-free Adaptation Framework for Medical Image Segmentation0
Consistency Regularization for Generalizable Source-free Domain Adaptation0
Show:102550
← PrevPage 15 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