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 121130 of 188 papers

TitleStatusHype
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
Source-free Domain Adaptation Requires Penalized Diversity0
Source-free Domain Adaptation via Distributional Alignment by Matching Batch Normalization Statistics0
Source-Free Domain Adaptation with Diffusion-Guided Source Data Generation0
Source Free Domain Adaptation with Image Translation0
Source-Free Video Domain Adaptation With Spatial-Temporal-Historical Consistency Learning0
Target-agnostic Source-free Domain Adaptation for Regression Tasks0
TempT: Temporal consistency for Test-time adaptation0
Test-Time Adaptation for Visual Document Understanding0
Show:102550
← PrevPage 13 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