Heedless Backbones

SETR

Paper | GitHub

axis

Select an option

Results

Parameters (M)

Images / Second

Publication Date

task

Select an option

---------

Semantic Segmentation

dataset

Select an option

---------

Cityscapes (val)

Cityscapes (test)

ADE20K (val)

ADE20K (test)

PASCAL VOC 2007 (val)

PASCAL VOC 2007 (test)

metric

Select an option

mIoU^ms

pAcc^ms

mAcc^ms

mIoU^ss

pAcc^ss

mAcc^ss

GFLOPs

resolution

Select an option

----------

512x2048

640x2560

axis

Select an option

Results

Parameters (M)

Images / Second

GFLOPs

Publication Date

Filters

pretrain dataset

Select an option

---------

MegData73M

JFT-3B

JFT-300M

ImageNet-1k

ImageNet-22k

pretrain method

Select an option

----------

Supervised

Sup. + TL

FCMAE

MAE

CL

Legend

Legend attribute

Select an option

Family

Pretrain Dataset

Pretrain Method

Semantic Segmentation Head

Semantic Segmentation Resolution

Semantic Segmentation Training Epochs

Legend attribute (second)

Select an option

----------

Pretrain Dataset

Pretrain Method

Semantic Segmentation Head

Semantic Segmentation Resolution

Semantic Segmentation Training Epochs

No Results

Cityscapes (val)

family	model	pretrain	train	gflops	mIoU^ms	pAcc^ms	mAcc^ms	mIoU^ss	pAcc^ss	mAcc^ss
FAN (Fully Attentional Networks)	FAN-T-Hybrid	IN-1k : Sup. : 300	Cityscapes (train) : 128 : 1024	None	—	—	—	81.2	—	—
FAN (Fully Attentional Networks)	FAN-S-Hybrid	IN-1k : Sup. : 300	Cityscapes (train) : 128 : 1024	None	—	—	—	81.5	—	—
FAN (Fully Attentional Networks)	FAN-B-Hybrid	IN-1k : Sup. : 300	Cityscapes (train) : 128 : 1024	None	—	—	—	82.2	—	—
FAN (Fully Attentional Networks)	FAN-L-Hybrid	IN-1k : Sup. : 300	Cityscapes (train) : 128 : 1024	None	—	—	—	82.3	—	—