Heedless Backbones

AnchorFormer Family

Paper | GitHub

axis

Select an option

Results

Parameters (M)

Images / Second

Publication Date

task

Select an option

---------

Object Detection

Instance Segmentation

Classification

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

head

Select an option

---------

UPerNet

Mask2Former

Panoptic FPN

SETR

resolution

Select an option

----------

512x2048

640x2560

axis

Select an option

Results

Parameters (M)

Images / Second

GFLOPs

Publication Date

Filters

pretrain dataset

Select an option

---------

ImageNet-1k

ImageNet-22k

JFT-300M

JFT-3B

MegData73M

pretrain method

Select an option

----------

Supervised

Sup. + TL

FCMAE

MAE

CL

MAP

Legend

Legend attribute

Select an option

Family

Pretrain Dataset

Semantic Segmentation Head

Semantic Segmentation Resolution

Semantic Segmentation Training Epochs

Legend attribute (second)

Select an option

----------

Family

Pretrain Method

Semantic Segmentation Head

Semantic Segmentation Resolution

Semantic Segmentation Training Epochs

model	params (m)	pretrain	head	train	GFLOPs	mIoU^ms
AnchorFormer-T	4.2	IN-1k : Sup. : 300	Panoptic FPN	ADE20K (train) : 128 : 512	193.7	43.81
AnchorFormer-S	18.6	IN-1k : Sup. : 300	UPerNet	ADE20K (train) : 128 : 512	928.1	46.28

model	params (m)	pretrain	finetune	gflops	IN-1k
AnchorFormer-T	4.2	IN-1k : Sup. : 300	— : — : —	0.7	81.12/93.86
AnchorFormer-S	18.6	IN-1k : Sup. : 300	— : — : —	2.7	84.69/96.82
AnchorFormer-B	63.5	IN-1k : Sup. : 300	— : — : —	9.2	86.62/97.84

ADE20K (val)

model	pretrain	head	train	gflops	mIoU^ms	pAcc^ms	mAcc^ms	mIoU^ss	pAcc^ss	mAcc^ss
AnchorFormer-T	IN-1k : Sup. : 300	Panoptic FPN	ADE20K (train) : 128 : 512	193.7	43.81	—	56.57	—	—	—
AnchorFormer-S	IN-1k : Sup. : 300	UPerNet	ADE20K (train) : 128 : 512	928.1	46.28	—	56.33	—	—	—