Heedless Backbones

Panoptic FPN

Paper | GitHub

axis

Select an option

Results

Parameters (M)

Images / Second

Publication Date

task

Select an option

---------

Instance Segmentation

Semantic Segmentation

Panoptic Segmentation

dataset

Select an option

---------

Cityscapes (val)

Cityscapes (test)

ADE20K (val)

ADE20K (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

---------

JFT-3B

ImageNet-1k

ImageNet-22k

JFT-300M

pretrain method

Select an option

----------

Supervised

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

ADE20K (val)

family	model	pretrain	train	gflops	mIoU^ms	pAcc^ms	mAcc^ms	mIoU^ss	pAcc^ss	mAcc^ss
Swin	Swin-T	IN-1k : Sup. : 300	ADE20K (train) : 64 : 512	182.0	—	—	—	41.5	—	—
Swin	Swin-B	IN-1k : Sup. : 300	ADE20K (train) : 64 : 512	422.0	—	—	—	46.0	—	—
Swin	Swin-S	IN-1k : Sup. : 300	ADE20K (train) : 64 : 512	274.0	—	—	—	45.2	—	—
CSWin	CSWin-T	IN-1k : Sup. : 300	ADE20K (train) : 64 : 512	202.0	—	—	—	48.2	—	—
CSWin	CSWin-S	IN-1k : Sup. : 300	ADE20K (train) : 64 : 512	271.0	—	—	—	49.2	—	—
CSWin	CSWin-B	IN-1k : Sup. : 300	ADE20K (train) : 64 : 512	464.0	—	—	—	49.9	—	—