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 7180 of 188 papers

TitleStatusHype
EIANet: A Novel Domain Adaptation Approach to Maximize Class Distinction with Neural Collapse PrinciplesCode0
1st Place Solution for ECCV 2022 OOD-CV Challenge Object Detection TrackCode0
Source-Free Domain Adaptation Guided by Vision and Vision-Language Pre-TrainingCode0
Effective Dual-Region Augmentation for Reduced Reliance on Large Amounts of Labeled DataCode0
A Comparison of Strategies for Source-Free Domain AdaptationCode0
SFDA-rPPG: Source-Free Domain Adaptive Remote Physiological Measurement with Spatio-Temporal ConsistencyCode0
Bridge then Begin Anew: Generating Target-relevant Intermediate Model for Source-free Visual Emotion AdaptationCode0
Agile Multi-Source-Free Domain AdaptationCode0
Self-training solutions for the ICCV 2023 GeoNet ChallengeCode0
SemEval-2021 Task 10: Source-Free Domain Adaptation for Semantic ProcessingCode0
Show:102550
← PrevPage 8 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