Heedless Backbones

VCMamba 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

No Results

model	params (m)	pretrain	finetune	gflops	IN-1k
VCMamba-S	10.5	IN-1k : Sup. : 300	— : — : —	1.1	78.7/—
VCMamba-M	21.0	IN-1k : Sup. : 300	— : — : —	2.3	81.5/—
VCMamba-B	31.5	IN-1k : Sup. : 300	— : — : —	4.0	82.6/—

ADE20K (val)

model	pretrain	head	train	gflops	mIoU^ms	pAcc^ms	mAcc^ms	mIoU^ss	pAcc^ss	mAcc^ss
VCMamba-S	IN-1k : Sup. : 300	Panoptic FPN	ADE20K (train) : 61 : 512	None	—	—	—	42.0	—	—
VCMamba-B	IN-1k : Sup. : 300	Panoptic FPN	ADE20K (train) : 61 : 512	None	—	—	—	47.1	—	—