Heedless Backbones

V2M 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

---------

ImageNet-1k

ImageNet-A

ImageNet-R

ImageNet-Sketch

ImageNet-C

ImageNet-C-bar

ImageNet-V2

ImageNet-ReaL

PASCAL VOC 2007 (val)

PASCAL VOC 2007 (test)

metric

Select an option

----------

Top-1

Top-5

GFLOPs

resolution

Select an option

----------

224x224

384x384

512x512

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

Classification Resolution

Legend attribute (second)

Select an option

----------

Family

Pretrain Method

Classification Resolution

model	params (m)	pretrain	finetune	GFLOPs	Top-1
V2M-T	7.0	IN-1k : Sup. : 300	— : — : —	1.9	76.2
V2M-S	26.0	IN-1k : Sup. : 300	— : — : —	5.9	80.5

model	params (m)	pretrain	finetune	gflops	IN-1k
V2M-T	7.0	IN-1k : Sup. : 300	— : — : —	1.9	76.2/93.1
V2M-S	26.0	IN-1k : Sup. : 300	— : — : —	5.9	80.5/—

ADE20K (val)

model	pretrain	head	train	gflops	mIoU^ms	pAcc^ms	mAcc^ms	mIoU^ss	pAcc^ss	mAcc^ss
V2M-T	IN-1k : Sup. : 300	UPerNet	ADE20K (train) : 128 : 512	None	42.0	—	—	41.4	—	—
V2M-S	IN-1k : Sup. : 300	UPerNet	ADE20K (train) : 128 : 512	None	46.1	—	—	45.1	—	—