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 151160 of 188 papers

TitleStatusHype
Source-Free Video Domain Adaptation With Spatial-Temporal-Historical Consistency Learning0
A Comparison of Strategies for Source-Free Domain Adaptation0
A Chebyshev Confidence Guided Source-Free Domain Adaptation Framework for Medical Image Segmentation0
Chaos to Order: A Label Propagation Perspective on Source-Free Domain Adaptation0
ViLAaD: Enhancing "Attracting and Dispersing'' Source-Free Domain Adaptation with Vision-and-Language Model0
Target-agnostic Source-free Domain Adaptation for Regression Tasks0
TempT: Temporal consistency for Test-time adaptation0
Test-Time Adaptation for Visual Document Understanding0
Test-time Batch Statistics Calibration for Covariate Shift0
The University of Arizona at SemEval-2021 Task 10: Applying Self-training, Active Learning and Data Augmentation to Source-free Domain Adaptation0
Show:102550
← PrevPage 16 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