Heedless Backbones

Vim-F(H) 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

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
Vim-Ti-F(H)	9.0	IN-1k : Sup. : 300	— : — : —	2.1	78.2
Vim-S-F(H)	37.0	IN-1k : Sup. : 300	— : — : —	6.8	81.6

model	params (m)	pretrain	finetune	gflops	IN-1k
Vim-Ti-F(H)	9.0	IN-1k : Sup. : 300	— : — : —	2.1	78.2/—
Vim-S-F(H)	37.0	IN-1k : Sup. : 300	— : — : —	6.8	81.6/—

COCO (val)

model	pretrain	head	train	gflops	mAP^b	AP^b₅₀	AP^b₇₅	mAP^b_s	mAP^b_m	mAP^b_l
Vim-Ti-F(H)	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	189.0	39.3	61.8	42.6	—	—	—
Vim-S-F(H)	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	275.0	42.9	65.4	47.1	—	—	—

COCO (val)

model	pretrain	head	train	gflops	mAP^m	AP^m₅₀	AP^m₇₅	mAP^m_s	mAP^m_m	mAP^m_l
Vim-Ti-F(H)	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	189.0	36.7	58.9	39.2	—	—	—
Vim-S-F(H)	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	275.0	39.3	62.2	42.2	—	—	—

ADE20K (val)

model	pretrain	head	train	gflops	mIoU^ms	pAcc^ms	mAcc^ms	mIoU^ss	pAcc^ss	mAcc^ss
Vim-S-F(H)	IN-1k : Sup. : 300	UPerNet	ADE20K (train) : 128 : 512	None	—	—	—	44.8	—	—