Heedless Backbones

LocalVim 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

---------

COCO (val)

COCO (test)

Cityscapes (val)

Cityscapes (test)

ADE20K (val)

ADE20K (test)

metric

Select an option

----------

mAP

AP₅₀

AP₇₅

mAP_s

mAP_m

mAP_l

GFLOPs

head

Select an option

---------

Mask R-CNN

Cascade Mask R-CNN

Mask2Former

HTC++

HTC

Panoptic FPN

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

Instance Head

Instance Training Epochs

Legend attribute (second)

Select an option

----------

Family

Pretrain Method

Instance Head

Instance Training Epochs

model	params (m)	pretrain	head	train	GFLOPs	mAP
LocalVim-T	8.0	IN-1k : Sup. : 300	Cascade Mask R-CNN	COCO (train) : 200	403.0	39.9

model	params (m)	pretrain	finetune	gflops	IN-1k
LocalVim-T	8.0	IN-1k : Sup. : 300	— : — : —	1.5	76.2/—
LocalVim-S	28.0	IN-1k : Sup. : 300	— : — : —	4.8	81.2/—

COCO (val)

model	pretrain	head	train	gflops	mAP^b	AP^b₅₀	AP^b₇₅	mAP^b_s	mAP^b_m	mAP^b_l
LocalVim-T	IN-1k : Sup. : 300	Cascade Mask R-CNN	COCO (train) : 200	403.0	45.3	66.2	49.1	26.0	49.5	61.7

COCO (val)

model	pretrain	head	train	gflops	mAP^m	AP^m₅₀	AP^m₇₅	mAP^m_s	mAP^m_m	mAP^m_l
LocalVim-T	IN-1k : Sup. : 300	Cascade Mask R-CNN	COCO (train) : 200	403.0	39.9	63.0	42.5	17.7	43.0	60.5

ADE20K (val)

model	pretrain	head	train	gflops	mIoU^ms	pAcc^ms	mAcc^ms	mIoU^ss	pAcc^ss	mAcc^ss
LocalVim-T	IN-1k : Sup. : 300	UPerNet	ADE20K (train) : 128 : 512	181.0	44.4	—	—	43.4	—	—
LocalVim-S	IN-1k : Sup. : 300	UPerNet	ADE20K (train) : 128 : 512	297.0	47.5	—	—	46.4	—	—