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)

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

family	model	params (m)	pretrain	head	train	GFLOPs	mIoU^ms
DAT++	DAT-T++	24.0	IN-1k : Sup. : 300	Panoptic FPN	ADE20K (train) : 64 : 512	212.0	48.8
DAT++	DAT-S++	53.0	IN-1k : Sup. : 300	Panoptic FPN	ADE20K (train) : 64 : 512	339.0	50.7
DAT++	DAT-B++	93.0	IN-1k : Sup. : 300	Panoptic FPN	ADE20K (train) : 64 : 512	508.0	51.1

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	—	—
BiFormer	BiFormer-S	IN-1k : Sup. : 300	ADE20K (train) : 128 : 512	None	—	—	—	48.9	—	—
BiFormer	BiFormer-B	IN-1k : Sup. : 300	ADE20K (train) : 128 : 512	None	—	—	—	49.9	—	—
RMT	RMT-T	IN-1k : Sup. : 300	ADE20K (train) : 64 : 512	33.7	—	—	—	46.4	—	—
RMT	RMT-S	IN-1k : Sup. : 300	ADE20K (train) : 64 : 512	180.0	—	—	—	49.4	—	—
RMT	RMT-B	IN-1k : Sup. : 300	ADE20K (train) : 64 : 512	294.0	—	—	—	50.4	—	—
RMT	RMT-L	IN-1k : Sup. : 300	ADE20K (train) : 64 : 512	482.0	—	—	—	51.4	—	—
DAT++	DAT-T++	IN-1k : Sup. : 300	ADE20K (train) : 64 : 512	212.0	48.8	—	—	48.4	—	—
DAT++	DAT-S++	IN-1k : Sup. : 300	ADE20K (train) : 64 : 512	339.0	50.7	—	—	49.9	—	—
DAT++	DAT-B++	IN-1k : Sup. : 300	ADE20K (train) : 64 : 512	508.0	51.1	—	—	50.4	—	—