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
49개Duke to MarketMarket to DukeSYNTHIA-to-CityscapesCityscapes to Foggy CityscapesGTAV-to-Cityscapes LabelsOffice-HomeMarket to MSMTImageNet-CVehicleID to VeRi-776Duke to MSMTSIM10K to CityscapesVeri-776 to VehicleID LargeVeri-776 to VehicleID MediumVisDA2017CUHK03 to MarketVehicleID to VERI-Wild LargeVehicleID to VERI-Wild MediumVehicleID to VERI-Wild SmallImageNet-RMarket to CUHK03Veri-776 to VehicleID SmallCUHK03 to MSMTCFC-DAODHMDB-UCFUCF-HMDBEPIC-KITCHENS-100Jester (Gesture Recognition)Office-31Office-Home (RS-UT imbalance)BDD100k to Cityscapes