Heedless Backbones

PASCAL VOC 2012 (val) Dataset

Select an option
Results
Parameters (M)
Images / Second
Publication Date
Select an option
---------
Semantic Segmentation
Select an option
mIoUms
pAccms
mAccms
mIoUss
pAccss
mAccss
GFLOPs
Select an option
---------
UPerNet
Mask2Former
Panoptic FPN
SETR
Trans2Seg
DeepLabv3
PSPNet
Linear
Select an option
----------
512x2048
640x2560
Select an option
Results
Parameters (M)
Images / Second
GFLOPs
Publication Date
Select an option
---------
ImageNet-1k
ImageNet-22k
JFT-300M
JFT-3B
MegData73M
WT++London
WT++
Select an option
----------
Supervised
Sup. + TL
FCMAE
MAE
CL
MAP
Self-Distillation
Select an option
Family
Pretrain Dataset
Pretrain Method
Semantic Segmentation Head
Semantic Segmentation Resolution
Semantic Segmentation Training Epochs
Select an option
----------
Pretrain Dataset
Pretrain Method
Semantic Segmentation Head
Semantic Segmentation Resolution
Semantic Segmentation Training Epochs

No Results

familymodelpretrainheadtraingflopsmIoUmspAccmsmAccmsmIoUsspAccssmAccss
MobileViTMobileViT-XXSIN-1k : Sup. : 300DeepLabv3PASCAL VOC 2012 (train + SBD + COCO) : 50 : 512None———73.6——
MobileViTMobileViT-XSIN-1k : Sup. : 300DeepLabv3PASCAL VOC 2012 (train + SBD + COCO) : 50 : 5125.7———77.1——
MobileViTMobileViT-SIN-1k : Sup. : 300DeepLabv3PASCAL VOC 2012 (train + SBD + COCO) : 50 : 512None———79.1——