Heedless Backbones

Mask R-CNN

Paper | GitHub

axis

Select an option

Results

Parameters (M)

Images / Second

Publication Date

task

Select an option

---------

Object Detection

Instance Segmentation

dataset

Select an option

---------

COCO (val)

COCO (test)

metric

Select an option

----------

mAP

AP₅₀

AP₇₅

mAP_s

mAP_m

mAP_l

GFLOPs

axis

Select an option

Results

Parameters (M)

Images / Second

GFLOPs

Publication Date

Filters

pretrain dataset

Select an option

---------

JFT-3B

ImageNet-1k

ImageNet-22k

JFT-300M

pretrain method

Select an option

----------

Supervised

FCMAE

MAE

CL

Legend

Legend attribute

Select an option

Family

Pretrain Dataset

Pretrain Method

Instance Head

Instance Training Epochs

Legend attribute (second)

Select an option

----------

Pretrain Dataset

Pretrain Method

Instance Head

Instance Training Epochs

family	model	params (m)	pretrain	head	train	GFLOPs	mAP
VMamba	VMamba-S	50.0	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	349.0	48.7
VMamba	VMamba-S	50.0	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 36	349.0	49.9
FocalNet	FocalNet-S-LRF	50.3	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	365.0	48.3
FocalNet	FocalNet-S-LRF	50.3	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 36	365.0	49.3
ConvNeXt V2	ConvNeXt V2-L	198.0	IN-1k : FCMAE : 1600	Mask R-CNN	COCO (train) : 36	875.0	54.4
TransNeXt	TransNeXt-S	49.7	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	516.0	51.1
MogaNet	MogaNet-XT	3.0	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	185.0	40.7
CSWin	CSWin-S	35.0	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	342.0	47.9
CSWin	CSWin-S	35.0	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 36	342.0	50.0
Hiera	Hiera-B	52.0	IN-1k : MAE : 1600	Mask R-CNN	COCO (train) : 100	600.0	52.2
CAFormer	CAFormer-S18	26.0	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 36	508.0	48.6
CSWin	CSWin-B	78.0	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	526.0	48.7
CSWin	CSWin-B	78.0	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 36	526.0	50.8
ConvNeXt V2	ConvNeXt V2-B	89.0	IN-1k : FCMAE : 1600	Mask R-CNN	COCO (train) : 36	486.0	52.9
FocalNet	FocalNet-T-LRF	28.6	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	268.0	46.1
FocalNet	FocalNet-T-LRF	28.6	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 36	268.0	48.0
MogaNet	MogaNet-T	5.2	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	192.0	42.6
Swin	Swin-B	88.0	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 50	700.0	50.1
Hiera	Hiera-L	214.0	IN-1k : MAE : 1600	Mask R-CNN	COCO (train) : 100	1200.0	55.0
CSWin	CSWin-T	23.0	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	279.0	46.7
CSWin	CSWin-T	23.0	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 36	279.0	49.0
Hiera	Hiera-B+	70.0	IN-1k : MAE : 1600	Mask R-CNN	COCO (train) : 100	600.0	53.5
TransNeXt	TransNeXt-T	28.2	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	356.0	49.9
FocalNet	FocalNet-S-SRF	50.3	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	356.0	48.0
FocalNet	FocalNet-S-SRF	50.3	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 36	356.0	48.9
Swin	Swin-L	197.0	IN-22k : Sup. : 90	Mask R-CNN	COCO (train) : 50	1100.0	52.4
ConvNeXt	ConvNeXt-T	29.0	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 36	262.0	46.2
Swin	Swin-S	50.0	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 36	359.0	48.5
Swin	Swin-T	29.0	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 36	267.0	46.0
ConvNeXt V2	ConvNeXt V2-H	660.0	IN-1k : FCMAE : 1600	Mask R-CNN	COCO (train) : 36	2525.0	55.7
MogaNet	MogaNet-B	43.8	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	373.0	47.9
FocalNet	FocalNet-B-LRF	88.7	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	507.0	49.0
FocalNet	FocalNet-B-LRF	88.7	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 36	507.0	49.8
FocalNet	FocalNet-T-SRF	28.4	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	268.0	45.9
FocalNet	FocalNet-T-SRF	28.4	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 36	268.0	47.6
InternImage	InternImage-B	97.0	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	501.0	48.8
InternImage	InternImage-B	97.0	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 36	501.0	50.3
VMamba	VMamba-T	30.0	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	271.0	47.3
VMamba	VMamba-T	30.0	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 36	271.0	48.8
MogaNet	MogaNet-S	25.3	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	272.0	46.7
FocalNet	FocalNet-B-SRF	88.1	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	496.0	48.8
FocalNet	FocalNet-B-SRF	88.1	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 36	496.0	49.6
ConvFormer	ConvFormer-S18	27.0	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 36	502.0	47.7
InternImage	InternImage-T	30.0	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	270.0	47.2
InternImage	InternImage-T	30.0	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 36	270.0	49.1
Swin	Swin-B	88.0	IN-22k : Sup. : 90	Mask R-CNN	COCO (train) : 50	700.0	51.4
InternImage	InternImage-S	50.0	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	340.0	47.8
InternImage	InternImage-S	50.0	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 36	340.0	49.7
VMamba	VMamba-B	89.0	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	485.0	49.2
TransNeXt	TransNeXt-B	89.7	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	728.0	51.7

COCO (val)

family	model	pretrain	train	gflops	mAP^b	AP^b₅₀	AP^b₇₅	mAP^b_s	mAP^b_m	mAP^b_l
TransNeXt	TransNeXt-T	IN-1k : Sup. : 300	COCO (train) : 12	356.0	49.9	71.5	54.9	—	—	—
TransNeXt	TransNeXt-S	IN-1k : Sup. : 300	COCO (train) : 12	516.0	51.1	72.6	56.2	—	—	—
TransNeXt	TransNeXt-B	IN-1k : Sup. : 300	COCO (train) : 12	728.0	51.7	73.2	56.9	—	—	—
ConvNeXt	ConvNeXt-T	IN-1k : Sup. : 300	COCO (train) : 36	262.0	46.2	67.9	50.8	—	—	—
Swin	Swin-T	IN-1k : Sup. : 300	COCO (train) : 36	267.0	46.0	68.1	50.3	—	—	—
Swin	Swin-B	IN-1k : Sup. : 300	COCO (train) : 50	700.0	50.1	—	—	—	—	—
Swin	Swin-B	IN-22k : Sup. : 90	COCO (train) : 50	700.0	51.4	—	—	—	—	—
Swin	Swin-S	IN-1k : Sup. : 300	COCO (train) : 36	359.0	48.5	—	—	—	—	—
Swin	Swin-L	IN-22k : Sup. : 90	COCO (train) : 50	1100.0	52.4	—	—	—	—	—
ConvNeXt V2	ConvNeXt V2-H	IN-1k : FCMAE : 1600	COCO (train) : 36	2525.0	55.7	75.2	61.8	—	—	—
ConvNeXt V2	ConvNeXt V2-L	IN-1k : FCMAE : 1600	COCO (train) : 36	875.0	54.4	73.9	60.4	—	—	—
ConvNeXt V2	ConvNeXt V2-B	IN-1k : FCMAE : 1600	COCO (train) : 36	486.0	52.9	72.6	58.9	—	—	—
Hiera	Hiera-B	IN-1k : MAE : 1600	COCO (train) : 100	600.0	52.2	—	—	—	—	—
Hiera	Hiera-B+	IN-1k : MAE : 1600	COCO (train) : 100	600.0	53.5	—	—	—	—	—
Hiera	Hiera-L	IN-1k : MAE : 1600	COCO (train) : 100	1200.0	55.0	—	—	—	—	—
InternImage	InternImage-T	IN-1k : Sup. : 300	COCO (train) : 12	270.0	47.2	69.0	52.1	—	—	—
InternImage	InternImage-T	IN-1k : Sup. : 300	COCO (train) : 36	270.0	49.1	70.4	54.1	—	—	—
InternImage	InternImage-S	IN-1k : Sup. : 300	COCO (train) : 12	340.0	47.8	69.8	52.8	—	—	—
InternImage	InternImage-S	IN-1k : Sup. : 300	COCO (train) : 36	340.0	49.7	71.1	54.5	—	—	—
InternImage	InternImage-B	IN-1k : Sup. : 300	COCO (train) : 12	501.0	48.8	70.9	54.0	—	—	—
InternImage	InternImage-B	IN-1k : Sup. : 300	COCO (train) : 36	501.0	50.3	71.4	55.3	—	—	—
FocalNet	FocalNet-T-LRF	IN-1k : Sup. : 300	COCO (train) : 12	268.0	46.1	68.2	50.6	—	—	—
FocalNet	FocalNet-T-LRF	IN-1k : Sup. : 300	COCO (train) : 36	268.0	48.0	69.7	53.0	—	—	—
FocalNet	FocalNet-T-SRF	IN-1k : Sup. : 300	COCO (train) : 12	268.0	45.9	68.3	50.1	—	—	—
FocalNet	FocalNet-T-SRF	IN-1k : Sup. : 300	COCO (train) : 36	268.0	47.6	69.5	52.0	—	—	—
FocalNet	FocalNet-S-SRF	IN-1k : Sup. : 300	COCO (train) : 12	356.0	48.0	69.9	52.7	—	—	—
FocalNet	FocalNet-S-SRF	IN-1k : Sup. : 300	COCO (train) : 36	356.0	48.9	70.1	53.7	—	—	—
FocalNet	FocalNet-S-LRF	IN-1k : Sup. : 300	COCO (train) : 12	365.0	48.3	70.5	53.1	—	—	—
FocalNet	FocalNet-S-LRF	IN-1k : Sup. : 300	COCO (train) : 36	365.0	49.3	70.7	54.2	—	—	—
FocalNet	FocalNet-B-LRF	IN-1k : Sup. : 300	COCO (train) : 12	507.0	49.0	70.9	53.9	—	—	—
FocalNet	FocalNet-B-LRF	IN-1k : Sup. : 300	COCO (train) : 36	507.0	49.8	70.9	54.6	—	—	—
FocalNet	FocalNet-B-SRF	IN-1k : Sup. : 300	COCO (train) : 12	496.0	48.8	70.7	53.5	—	—	—
FocalNet	FocalNet-B-SRF	IN-1k : Sup. : 300	COCO (train) : 36	496.0	49.6	70.6	54.1	—	—	—
CSWin	CSWin-T	IN-1k : Sup. : 300	COCO (train) : 12	279.0	46.7	68.6	51.3	—	—	—
CSWin	CSWin-T	IN-1k : Sup. : 300	COCO (train) : 36	279.0	49.0	70.7	53.7	—	—	—
CSWin	CSWin-S	IN-1k : Sup. : 300	COCO (train) : 12	342.0	47.9	70.1	52.6	—	—	—
CSWin	CSWin-S	IN-1k : Sup. : 300	COCO (train) : 36	342.0	50.0	71.3	54.7	—	—	—
CSWin	CSWin-B	IN-1k : Sup. : 300	COCO (train) : 12	526.0	48.7	70.4	53.9	—	—	—
CSWin	CSWin-B	IN-1k : Sup. : 300	COCO (train) : 36	526.0	50.8	72.1	55.8	—	—	—
CAFormer	CAFormer-S18	IN-1k : Sup. : 300	COCO (train) : 36	508.0	48.6	70.5	53.4	—	—	—
ConvFormer	ConvFormer-S18	IN-1k : Sup. : 300	COCO (train) : 36	502.0	47.7	69.6	52.3	—	—	—
MogaNet	MogaNet-XT	IN-1k : Sup. : 300	COCO (train) : 12	185.0	40.7	62.3	44.4	—	—	—
MogaNet	MogaNet-T	IN-1k : Sup. : 300	COCO (train) : 12	192.0	42.6	64.0	46.4	—	—	—
MogaNet	MogaNet-S	IN-1k : Sup. : 300	COCO (train) : 12	272.0	46.7	68.0	51.3	—	—	—
MogaNet	MogaNet-B	IN-1k : Sup. : 300	COCO (train) : 12	373.0	47.9	70.0	52.7	—	—	—
VMamba	VMamba-T	IN-1k : Sup. : 300	COCO (train) : 12	271.0	47.3	69.3	52.0	—	—	—
VMamba	VMamba-T	IN-1k : Sup. : 300	COCO (train) : 36	271.0	48.8	70.4	53.5	—	—	—
VMamba	VMamba-S	IN-1k : Sup. : 300	COCO (train) : 12	349.0	48.7	70.0	53.4	—	—	—
VMamba	VMamba-S	IN-1k : Sup. : 300	COCO (train) : 36	349.0	49.9	70.9	54.7	—	—	—
VMamba	VMamba-B	IN-1k : Sup. : 300	COCO (train) : 12	485.0	49.2	71.4	54.0	—	—	—

COCO (val)

family	model	pretrain	train	gflops	mAP^m	AP^m₅₀	AP^m₇₅	mAP^m_s	mAP^m_m	mAP^m_l
TransNeXt	TransNeXt-T	IN-1k : Sup. : 300	COCO (train) : 12	356.0	44.6	68.6	48.1	—	—	—
TransNeXt	TransNeXt-S	IN-1k : Sup. : 300	COCO (train) : 12	516.0	45.5	69.8	49.1	—	—	—
TransNeXt	TransNeXt-B	IN-1k : Sup. : 300	COCO (train) : 12	728.0	45.9	70.5	49.7	—	—	—
ConvNeXt	ConvNeXt-T	IN-1k : Sup. : 300	COCO (train) : 36	262.0	41.7	65.0	44.9	—	—	—
Swin	Swin-T	IN-1k : Sup. : 300	COCO (train) : 36	267.0	41.6	65.1	44.9	—	—	—
Swin	Swin-B	IN-1k : Sup. : 300	COCO (train) : 50	600.0	44.5	—	—	—	—	—
Swin	Swin-B	IN-22k : Sup. : 90	COCO (train) : 50	700.0	45.4	—	—	—	—	—
Swin	Swin-S	IN-1k : Sup. : 300	COCO (train) : 36	359.0	43.3	—	—	—	—	—
Swin	Swin-L	IN-22k : Sup. : 90	COCO (train) : 50	1100.0	46.2	—	—	—	—	—
ConvNeXt V2	ConvNeXt V2-H	IN-1k : FCMAE : 1600	COCO (train) : 36	2525.0	48.9	72.8	53.6	—	—	—
ConvNeXt V2	ConvNeXt V2-L	IN-1k : FCMAE : 1600	COCO (train) : 36	875.0	47.7	71.4	52.3	—	—	—
ConvNeXt V2	ConvNeXt V2-B	IN-1k : FCMAE : 1600	COCO (train) : 36	486.0	46.6	70.0	51.1	—	—	—
Hiera	Hiera-B	IN-1k : MAE : 1600	COCO (train) : 100	600.0	46.3	—	—	—	—	—
Hiera	Hiera-B+	IN-1k : MAE : 1600	COCO (train) : 100	600.0	47.3	—	—	—	—	—
Hiera	Hiera-L	IN-1k : MAE : 1600	COCO (train) : 100	1200.0	48.6	—	—	—	—	—
InternImage	InternImage-T	IN-1k : Sup. : 300	COCO (train) : 12	270.0	42.5	66.1	45.8	—	—	—
InternImage	InternImage-T	IN-1k : Sup. : 300	COCO (train) : 36	270.0	43.7	67.3	47.3	—	—	—
InternImage	InternImage-S	IN-1k : Sup. : 300	COCO (train) : 12	340.0	43.3	67.1	46.7	—	—	—
InternImage	InternImage-S	IN-1k : Sup. : 300	COCO (train) : 36	340.0	44.5	68.5	47.8	—	—	—
InternImage	InternImage-B	IN-1k : Sup. : 300	COCO (train) : 12	501.0	44.0	67.8	47.4	—	—	—
InternImage	InternImage-B	IN-1k : Sup. : 300	COCO (train) : 36	501.0	44.8	68.7	48.0	—	—	—
FocalNet	FocalNet-T-LRF	IN-1k : Sup. : 300	COCO (train) : 12	268.0	41.5	65.1	44.5	—	—	—
FocalNet	FocalNet-T-LRF	IN-1k : Sup. : 300	COCO (train) : 36	268.0	42.9	66.5	46.1	—	—	—
FocalNet	FocalNet-T-SRF	IN-1k : Sup. : 300	COCO (train) : 36	268.0	41.3	65.0	44.3	—	—	—
FocalNet	FocalNet-T-SRF	IN-1k : Sup. : 300	COCO (train) : 36	268.0	42.6	66.5	45.6	—	—	—
FocalNet	FocalNet-S-SRF	IN-1k : Sup. : 300	COCO (train) : 12	56.0	42.7	67.1	45.7	—	—	—
FocalNet	FocalNet-S-SRF	IN-1k : Sup. : 300	COCO (train) : 36	56.0	43.6	67.1	47.1	—	—	—
FocalNet	FocalNet-S-LRF	IN-1k : Sup. : 300	COCO (train) : 12	365.0	43.1	67.4	46.2	—	—	—
FocalNet	FocalNet-S-LRF	IN-1k : Sup. : 300	COCO (train) : 36	365.0	43.8	67.9	47.4	—	—	—
FocalNet	FocalNet-B-LRF	IN-1k : Sup. : 300	COCO (train) : 12	507.0	43.5	67.9	46.7	—	—	—
FocalNet	FocalNet-B-LRF	IN-1k : Sup. : 300	COCO (train) : 36	507.0	44.1	68.2	47.2	—	—	—
FocalNet	FocalNet-B-SRF	IN-1k : Sup. : 300	COCO (train) : 12	496.0	43.3	67.5	46.5	—	—	—
FocalNet	FocalNet-B-SRF	IN-1k : Sup. : 300	COCO (train) : 36	496.0	44.1	68.0	47.2	—	—	—
CSWin	CSWin-T	IN-1k : Sup. : 300	COCO (train) : 12	279.0	42.2	65.6	45.4	—	—	—
CSWin	CSWin-T	IN-1k : Sup. : 300	COCO (train) : 36	279.0	43.6	67.9	46.6	—	—	—
CSWin	CSWin-S	IN-1k : Sup. : 300	COCO (train) : 12	342.0	43.2	67.1	46.2	—	—	—
CSWin	CSWin-S	IN-1k : Sup. : 300	COCO (train) : 36	342.0	44.5	68.4	47.7	—	—	—
CSWin	CSWin-B	IN-1k : Sup. : 300	COCO (train) : 12	526.0	43.9	67.8	47.3	—	—	—
CSWin	CSWin-B	IN-1k : Sup. : 300	COCO (train) : 36	526.0	44.9	69.1	48.3	—	—	—
CAFormer	CAFormer-S18	IN-1k : Sup. : 300	COCO (train) : 36	508.0	43.7	67.5	47.4	—	—	—
ConvFormer	ConvFormer-S18	IN-1k : Sup. : 300	COCO (train) : 36	502.0	42.6	66.3	45.9	—	—	—
MogaNet	MogaNet-XT	IN-1k : Sup. : 300	COCO (train) : 12	185.0	37.6	59.6	40.2	—	—	—
MogaNet	MogaNet-T	IN-1k : Sup. : 300	COCO (train) : 12	192.0	39.1	61.3	42.0	—	—	—
MogaNet	MogaNet-S	IN-1k : Sup. : 300	COCO (train) : 12	272.0	42.2	65.4	45.5	—	—	—
MogaNet	MogaNet-B	IN-1k : Sup. : 300	COCO (train) : 12	373.0	43.2	67.0	46.6	—	—	—
VMamba	VMamba-T	IN-1k : Sup. : 300	COCO (train) : 12	271.0	42.7	66.4	45.9	—	—	—
VMamba	VMamba-T	IN-1k : Sup. : 300	COCO (train) : 36	271.0	43.7	67.4	47.0	—	—	—
VMamba	VMamba-S	IN-1k : Sup. : 300	COCO (train) : 12	349.0	43.7	67.3	47.0	—	—	—
VMamba	VMamba-S	IN-1k : Sup. : 300	COCO (train) : 36	349.0	44.2	68.2	47.7	—	—	—
VMamba	VMamba-B	IN-1k : Sup. : 300	COCO (train) : 12	485.0	44.1	68.3	47.7	—	—	—