TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

SotA/Computer Vision/Source-Free Domain Adaptation

Source-Free Domain Adaptation

20 benchmarks188 papers

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

Benchmarks

Source-Free Domain Adaptation on Cityscapes to Foggy Cityscapes

AP50

Source-Free Domain Adaptation on VisDA-2017

Accuracy

Source-Free Domain Adaptation on InBreast

R@0.05R@0.3R@0.5R@1.0AUCF1-score

Source-Free Domain Adaptation on PACS

Average Accuracy

Source-Free Domain Adaptation on Cityscapes to ACDC

mIoU

Source-Free Domain Adaptation on VIPER-to-Cityscapes

mIoU

Source-Free Domain Adaptation on Cityscapes to Dark Zurich

mIoU

Source-Free Domain Adaptation on GTA5 to Cityscapes

mIoU

Source-Free Domain Adaptation on SYNTHIA-to-Cityscapes

mIoU

Source-Free Domain Adaptation on SynLiDAR-to-SemanticKITTI

mIoU

Source-Free Domain Adaptation on SynLiDAR-to-SemanticPOSS

mIoU

Source-Free Domain Adaptation on nuScenes-to-Pandaset

mIoU

Source-Free Domain Adaptation on nuScenes-to-SemanticKITTI

mIoU

Source-Free Domain Adaptation on nuScenes-to-SemanticPOSS

mIoU

Source-Free Domain Adaptation on nuScenes-to-Waymo Open Dataset

mIoU