Papers with Code · CC BY-SA 4.0
Unsupervised Domain Adaptation
Unsupervised Domain Adaptation is a learning framework to transfer knowledge learned from source domains with a large number of annotated training examples to target domains with unlabeled data only.
<span class="description-source">Source: Domain-Specific Batch Normalization for Unsupervised Domain Adaptation </span>
데이터셋
49개Cityscapes-to-OxfordCarDomainNetvirtual KITTI to KITTI (MDE)PACSSIM10K to BDD100KKitti to CityscapesOOD-CVPascal VOC to Clipart1KPreSIL to KITTIClonedPersonFHISTGTA5+Synscapes+Urbansyn to CityscapesGTA5-to-CityscapesImageNet-AMSCOCO to FLIR ADASPortraits (over time)UDA-CHVehicle to VERI-WildVisDA-2017