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
ViLAaD: Enhancing "Attracting and Dispersing'' Source-Free Domain Adaptation with Vision-and-Language Model0
Chaos to Order: A Label Propagation Perspective on Source-Free Domain Adaptation0
When Source-Free Domain Adaptation Meets Learning with Noisy Labels0
YNU-HPCC at SemEval-2021 Task 10: Using a Transformer-based Source-Free Domain Adaptation Model for Semantic Processing0
FACT: Federated Adversarial Cross TrainingCode0
Unveiling the Unknown: Unleashing the Power of Unknown to Known in Open-Set Source-Free Domain AdaptationCode0
Empowering Source-Free Domain Adaptation with MLLM-driven Curriculum LearningCode0
Rethinking the Role of Pre-Trained Networks in Source-Free Domain AdaptationCode0
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
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