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 181188 of 188 papers

TitleStatusHype
Trust your Good Friends: Source-free Domain Adaptation by Reciprocal Neighborhood Clustering0
In Search for a Generalizable Method for Source Free Domain Adaptation0
Improving Online Source-free Domain Adaptation for Object Detection by Unsupervised Data Acquisition0
Annotator: A Generic Active Learning Baseline for LiDAR Semantic Segmentation0
Imbalance-Agnostic Source-Free Domain Adaptation via Avatar Prototype Alignment0
Uncertainty-Guided Mixup for Semi-Supervised Domain Adaptation without Source Data0
Revisiting Source-Free Domain Adaptation: Insights into Representativeness, Generalization, and Variety0
IITK at SemEval-2021 Task 10: Source-Free Unsupervised Domain Adaptation using Class Prototypes0
Show:102550
← PrevPage 19 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