List your company
ResearchFormerly WizWand

Panoptic Segmentation on ADE20K 15 (val)

51.5PQOneFormer
47.96448.88249.850.718Nov 10, 2022
Updated 8mo ago

Evaluation results

MethodLinks
OneFormerBackbone=DINAT-L, #Params=223M, Crop Size=1280x1280, Extra Data=false, Training Protocol=Joint Training2022.1151.5
OneFormerBackbone=Swin-L, #Params=219M, Crop Size=1280x1280, Extra Data=false, Training Protocol=Joint Training2022.1151.4
OneFormerBackbone=DINAT-L, #Params=223M, Crop Size=896x896, Extra Data=false, Training Protocol=Joint Training2022.1151.2
OneFormerBackbone=Swin-L, #Params=219M, Crop Size=896x896, Extra Data=false, Training Protocol=Joint Training2022.1151.1
kMaX-DeepLabBackbone=ConvNeXt-L, #Params=232M, Crop Size=1281x1281, Extra Data=false, Training Protocol=Individual Training2022.1150.9
OneFormerBackbone=DINAT-L, #Params=223M, Crop Size=640x640, Extra Data=false, Training Protocol=Joint Training2022.1150.5
OneFormerBackbone=ConvNeXt-XL, #Params=372M, Crop Size=640x640, Extra Data=false, Training Protocol=Joint Training2022.1150.1
OneFormerBackbone=ConvNeXt-L, #Params=220M, Crop Size=640x640, Extra Data=false, Training Protocol=Joint Training2022.1150
OneFormerBackbone=Swin-L, #Params=219M, Crop Size=640x640, Extra Data=false, Training Protocol=Joint Training2022.1149.8
kMaX-DeepLabBackbone=ConvNeXt-L†, #Params=232M, Crop Size=641x641, Extra Data=false, Training Protocol=Individual Training2022.1148.7
Mask2Former-PanopticBackbone=Swin-L, #Params=216M, Crop Size=640x640, Extra Data=false, Training Protocol=Individual Training2022.1148.1