Heedless Backbones

LocalVMamba 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

---------

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

Classification Resolution

Legend attribute (second)

Select an option

----------

Family

Pretrain Method

Classification Resolution

model	params (m)	pretrain	finetune	GFLOPs	Top-1
LocalVMamba-T	26.0	IN-1k : Sup. : 300	— : — : —	5.7	82.7
LocalVMamba-S	50.0	IN-1k : Sup. : 300	— : — : —	11.4	83.7

model	params (m)	pretrain	finetune	gflops	IN-1k
LocalVMamba-T	26.0	IN-1k : Sup. : 300	— : — : —	5.7	82.7/—
LocalVMamba-S	50.0	IN-1k : Sup. : 300	— : — : —	11.4	83.7/—

COCO (val)

model	pretrain	head	train	gflops	mAP^b	AP^b₅₀	AP^b₇₅	mAP^b_s	mAP^b_m	mAP^b_l
LocalVMamba-T	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	291.0	46.7	68.7	50.8	—	—	—
LocalVMamba-T	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 36	291.0	48.7	70.1	53.0	—	—	—
LocalVMamba-S	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	414.0	48.4	69.9	52.7	—	—	—
LocalVMamba-S	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 36	414.0	49.9	70.5	54.4	—	—	—

COCO (val)

model	pretrain	head	train	gflops	mAP^m	AP^m₅₀	AP^m₇₅	mAP^m_s	mAP^m_m	mAP^m_l
LocalVMamba-T	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	291.0	42.2	65.7	45.5	—	—	—
LocalVMamba-T	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 36	291.0	43.4	67.0	46.4	—	—	—
LocalVMamba-S	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	414.0	43.2	66.7	46.5	—	—	—
LocalVMamba-S	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 36	414.0	44.1	67.8	47.4	—	—	—

ADE20K (val)

model	pretrain	head	train	gflops	mIoU^ms	pAcc^ms	mAcc^ms	mIoU^ss	pAcc^ss	mAcc^ss
LocalVMamba-T	IN-1k : Sup. : 300	UPerNet	ADE20K (train) : 128 : 512	970.0	49.1	—	—	47.9	—	—
LocalVMamba-S	IN-1k : Sup. : 300	UPerNet	ADE20K (train) : 128 : 512	1095.0	51.0	—	—	50.0	—	—