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

---------

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

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

No Results

model	params (m)	pretrain	finetune	gflops	IN-1k
V2M-S*	30.0	IN-1k : Sup. : 300	— : — : —	5.4	82.9/—
V2M-B*	50.0	IN-1k : Sup. : 300	— : — : —	9.6	83.8/—

COCO (val)

model	pretrain	head	train	gflops	mAP^b	AP^b₅₀	AP^b₇₅	mAP^b_s	mAP^b_m	mAP^b_l
V2M-S*	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	None	47.6	69.4	52.2	—	—	—
V2M-S*	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 36	None	49.0	70.6	53.5	—	—	—
V2M-B*	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	None	48.9	70.2	53.6	—	—	—
V2M-B*	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 36	None	50.0	70.9	54.8	—	—	—

COCO (val)

model	pretrain	head	train	gflops	mAP^m	AP^m₅₀	AP^m₇₅	mAP^m_s	mAP^m_m	mAP^m_l
V2M-S*	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	None	42.9	66.5	46.3	—	—	—
V2M-S*	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 36	None	43.8	67.5	47.2	—	—	—
V2M-B*	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	None	43.8	67.5	47.1	—	—	—
V2M-B*	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 36	None	44.3	68.4	47.8	—	—	—

ADE20K (val)

model	pretrain	head	train	gflops	mIoU^ms	pAcc^ms	mAcc^ms	mIoU^ss	pAcc^ss	mAcc^ss
V2M-S*	IN-1k : Sup. : 300	UPerNet	ADE20K (train) : 128 : 512	None	49.0	—	—	48.2	—	—
V2M-B*	IN-1k : Sup. : 300	UPerNet	ADE20K (train) : 128 : 512	None	51.3	—	—	50.8	—	—