Cascade 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)

PASCAL VOC 2007 (val)

PASCAL VOC 2007 (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

---------

ImageNet-1k

ImageNet-22k

JFT-300M

JFT-3B

MegData73M

pretrain method

Select an option

----------

Supervised

Sup. + TL

FCMAE

MAE

MAP

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
Swin	Swin-T	29.0	IN-1k : Sup. : 300	Cascade Mask R-CNN	COCO (train) : 36	745.0	50.4
RepLKNet	RepLKNet-31B	79.0	IN-22k : Sup. : 90	Cascade Mask R-CNN	COCO (train) : 36	965.0	53.0
CAFormer	CAFormer-S18	26.0	IN-1k : Sup. : 300	Cascade Mask R-CNN	COCO (train) : 36	1466.0	52.3
Iwin Transformer	Iwin-T	30.2	IN-1k : Sup. : 300	Cascade Mask R-CNN	COCO (train) : 12	747.0	47.2
Iwin Transformer	Iwin-T	30.2	IN-1k : Sup. : 300	Cascade Mask R-CNN	COCO (train) : 36	747.0	49.4
MaxViT	MaxViT-S	69.0	IN-1k : Sup. : 300	Cascade Mask R-CNN	COCO (train) : 36	595.0	53.1
NAT	NAT-T	28.0	IN-1k : Sup. : 300	Cascade Mask R-CNN	COCO (train) : 36	737.0	51.4
InternImage	InternImage-XL	335.0	IN-22k : Sup. : 90	Cascade Mask R-CNN	COCO (train) : 12	1782.0	55.3
InternImage	InternImage-XL	335.0	IN-22k : Sup. : 90	Cascade Mask R-CNN	COCO (train) : 36	1782.0	56.2
ConvNeXt	ConvNeXt-L	198.0	IN-22k : Sup. : 90	Cascade Mask R-CNN	COCO (train) : 36	1354.0	54.8
RepLKNet	RepLKNet-31L	172.0	IN-22k : Sup. : 90	Cascade Mask R-CNN	COCO (train) : 36	1321.0	53.9
ConvNeXt	ConvNeXt-S	50.0	IN-1k : Sup. : 300	Cascade Mask R-CNN	COCO (train) : 36	827.0	51.9
Swin	Swin-B	88.0	IN-22k : Sup. : 90	Cascade Mask R-CNN	COCO (train) : 36	982.0	53.0
Swin	Swin-B	88.0	IN-22k : Sup. : 90	Cascade Mask R-CNN	COCO (train) : 50	982.0	54.0
DAT++	DAT-B++	93.0	IN-1k : Sup. : 300	Cascade Mask R-CNN	COCO (train) : 36	1059.0	54.5
A2Mamba	A2Mamba-B	51.0	IN-1k : Sup. : 300	Cascade Mask R-CNN	COCO (train) : 36	889.0	55.4
MogaNet	MogaNet-S	25.3	IN-1k : Sup. : 300	Cascade Mask R-CNN	COCO (train) : 36	750.0	51.6
Iwin Transformer	Iwin-S	51.6	IN-1k : Sup. : 300	Cascade Mask R-CNN	COCO (train) : 36	837.0	49.4
UniRepLKNet	UniRepLKNet-B	97.9	IN-22k : Sup. : 90	Cascade Mask R-CNN	COCO (train) : 36	978.0	54.8
DAT	DAT-B	88.0	IN-1k : Sup. : 300	Cascade Mask R-CNN	COCO (train) : 36	1003.0	53.0
MogaNet	MogaNet-XL	180.8	IN-22k : Sup. : 90	Cascade Mask R-CNN	COCO (train) : 36	1355.0	56.2
FocalNet	FocalNet-T-SRF	28.4	IN-1k : Sup. : 300	Cascade Mask R-CNN	COCO (train) : 36	746.0	51.5
RMT	RMT-S	27.0	IN-1k : Sup. : 300	Cascade Mask R-CNN	COCO (train) : 36	741.0	53.2
UniRepLKNet	UniRepLKNet-XL	386.4	IN-22k : Sup. : 90	Cascade Mask R-CNN	COCO (train) : 36	1952.0	56.4
UniRepLKNet	UniRepLKNet-L	218.3	IN-22k : Sup. : 90	Cascade Mask R-CNN	COCO (train) : 36	1385.0	55.8
CSWin	CSWin-T	23.0	IN-1k : Sup. : 300	Cascade Mask R-CNN	COCO (train) : 36	757.0	52.5
NAT	NAT-B	90.0	IN-1k : Sup. : 300	Cascade Mask R-CNN	COCO (train) : 36	931.0	52.5
RepLKNet	RepLKNet-31B	79.0	IN-1k : Sup. : 300	Cascade Mask R-CNN	COCO (train) : 36	965.0	52.2
MogaNet	MogaNet-B	43.8	IN-1k : Sup. : 300	Cascade Mask R-CNN	COCO (train) : 36	851.0	52.6
ConvNeXt	ConvNeXt-B	89.0	IN-22k : Sup. : 90	Cascade Mask R-CNN	COCO (train) : 36	964.0	54.0
MA ViT	MA ViT-B	50.0	IN-1k : Sup. : 300	Cascade Mask R-CNN	COCO (train) : 36	851.0	55.5
MA ViT	MA ViT-S	27.0	IN-1k : Sup. : 300	Cascade Mask R-CNN	COCO (train) : 36	741.0	54.2
ConvFormer	ConvFormer-M36	57.0	IN-1k : Sup. : 300	Cascade Mask R-CNN	COCO (train) : 36	1824.0	53.0
Swin	Swin-L	197.0	IN-22k : Sup. : 90	Cascade Mask R-CNN	COCO (train) : 36	1382.0	53.9
Swin	Swin-L	197.0	IN-22k : Sup. : 90	Cascade Mask R-CNN	COCO (train) : 50	1382.0	54.8
ConvNeXt	ConvNeXt-T	29.0	IN-1k : Sup. : 300	Cascade Mask R-CNN	COCO (train) : 36	741.0	50.4
MogaNet	MogaNet-L	82.5	IN-1k : Sup. : 300	Cascade Mask R-CNN	COCO (train) : 36	974.0	53.3
UniRepLKNet	UniRepLKNet-S	55.6	IN-1k : Sup. : 300	Cascade Mask R-CNN	COCO (train) : 36	835.0	53.0
FocalNet	FocalNet-T-LRF	28.6	IN-1k : Sup. : 300	Cascade Mask R-CNN	COCO (train) : 36	751.0	51.5
UniRepLKNet	UniRepLKNet-T	31.0	IN-1k : Sup. : 300	Cascade Mask R-CNN	COCO (train) : 36	749.0	51.8
CAFormer	CAFormer-M36	56.0	IN-1k : Sup. : 300	Cascade Mask R-CNN	COCO (train) : 36	1840.0	53.8
ConvNeXt	ConvNeXt-XL	350.0	IN-22k : Sup. : 90	Cascade Mask R-CNN	COCO (train) : 36	1898.0	55.2
LocalVim	LocalVim-T	8.0	IN-1k : Sup. : 300	Cascade Mask R-CNN	COCO (train) : 200	403.0	45.3
MA ViT	MA ViT-L	98.0	IN-1k : Sup. : 300	Cascade Mask R-CNN	COCO (train) : 36	979.0	56.0
CAFormer	CAFormer-S36	39.0	IN-1k : Sup. : 300	Cascade Mask R-CNN	COCO (train) : 36	1622.0	53.2
SSViT	SSViT-S	27.0	IN-1k : Sup. : 300	Cascade Mask R-CNN	COCO (train) : 36	745.0	53.8
NAT	NAT-M	20.0	IN-1k : Sup. : 300	Cascade Mask R-CNN	COCO (train) : 36	704.0	50.3
A2Mamba	A2Mamba-L	95.0	IN-1k : Sup. : 300	Cascade Mask R-CNN	COCO (train) : 36	1027.0	55.6
ConvNeXt	ConvNeXt-B	89.0	IN-1k : Sup. : 300	Cascade Mask R-CNN	COCO (train) : 36	964.0	52.7
SSViT	SSViT-B	57.0	IN-1k : Sup. : 300	Cascade Mask R-CNN	COCO (train) : 36	861.0	54.9
DAT	DAT-S	50.0	IN-1k : Sup. : 300	Cascade Mask R-CNN	COCO (train) : 36	857.0	52.7
RMT	RMT-B	54.0	IN-1k : Sup. : 300	Cascade Mask R-CNN	COCO (train) : 36	852.0	54.5
DAT++	DAT-S++	53.0	IN-1k : Sup. : 300	Cascade Mask R-CNN	COCO (train) : 36	895.0	54.2
DAT++	DAT-T++	24.0	IN-1k : Sup. : 300	Cascade Mask R-CNN	COCO (train) : 12	771.0	52.2
DAT++	DAT-T++	24.0	IN-1k : Sup. : 300	Cascade Mask R-CNN	COCO (train) : 36	771.0	53.0
ConvFormer	ConvFormer-S18	27.0	IN-1k : Sup. : 300	Cascade Mask R-CNN	COCO (train) : 36	1458.0	51.5
CSWin	CSWin-S	35.0	IN-1k : Sup. : 300	Cascade Mask R-CNN	COCO (train) : 36	820.0	53.7
MaxViT	MaxViT-B	120.0	IN-1k : Sup. : 300	Cascade Mask R-CNN	COCO (train) : 36	856.0	53.4
UniRepLKNet	UniRepLKNet-S	55.6	IN-22k : Sup. : 90	Cascade Mask R-CNN	COCO (train) : 36	835.0	54.3
MaxViT	MaxViT-T	31.0	IN-1k : Sup. : 300	Cascade Mask R-CNN	COCO (train) : 36	475.0	52.1
NAT	NAT-S	51.0	IN-1k : Sup. : 300	Cascade Mask R-CNN	COCO (train) : 36	809.0	52.0
CSWin	CSWin-B	78.0	IN-1k : Sup. : 300	Cascade Mask R-CNN	COCO (train) : 36	1004.0	53.9
ConvFormer	ConvFormer-S36	40.0	IN-1k : Sup. : 300	Cascade Mask R-CNN	COCO (train) : 36	1610.0	52.5
InternImage	InternImage-L	223.0	IN-22k : Sup. : 90	Cascade Mask R-CNN	COCO (train) : 12	1399.0	54.9
InternImage	InternImage-L	223.0	IN-22k : Sup. : 90	Cascade Mask R-CNN	COCO (train) : 36	1399.0	56.1
Swin	Swin-S	50.0	IN-1k : Sup. : 300	Cascade Mask R-CNN	COCO (train) : 36	838.0	51.9
DAT	DAT-T	29.0	IN-1k : Sup. : 300	Cascade Mask R-CNN	COCO (train) : 12	750.0	49.1
DAT	DAT-T	29.0	IN-1k : Sup. : 300	Cascade Mask R-CNN	COCO (train) : 36	750.0	51.3
RepLKNet	RepLKNet-XL	335.0	MegData73M : Sup. : 15	Cascade Mask R-CNN	COCO (train) : 36	1958.0	55.5
A2Mamba	A2Mamba-S	31.0	IN-1k : Sup. : 300	Cascade Mask R-CNN	COCO (train) : 36	762.0	54.0
UniConvNet	UniConvNet-L	201.8	IN-22k : Sup. : 90	Cascade Mask R-CNN	COCO (train) : 12	1288.0	55.7
UniConvNet	UniConvNet-L	201.8	IN-22k : Sup. : 90	Cascade Mask R-CNN	COCO (train) : 36	1288.0	56.6
Swin	Swin-B	88.0	IN-1k : Sup. : 300	Cascade Mask R-CNN	COCO (train) : 36	982.0	51.9
Swin	Swin-B	88.0	IN-1k : Sup. : 300	Cascade Mask R-CNN	COCO (train) : 50	982.0	52.7

COCO (val)

family	model	pretrain	train	gflops	mAP^b	AP^b₅₀	AP^b₇₅	mAP^b_s	mAP^b_m	mAP^b_l
ConvNeXt	ConvNeXt-L	IN-22k : Sup. : 90	COCO (train) : 36	1354.0	54.8	73.8	59.8	—	—	—
ConvNeXt	ConvNeXt-B	IN-1k : Sup. : 300	COCO (train) : 36	964.0	52.7	71.3	57.2	—	—	—
ConvNeXt	ConvNeXt-B	IN-22k : Sup. : 90	COCO (train) : 36	964.0	54.0	73.1	58.8	—	—	—
ConvNeXt	ConvNeXt-S	IN-1k : Sup. : 300	COCO (train) : 36	827.0	51.9	70.8	56.5	—	—	—
ConvNeXt	ConvNeXt-T	IN-1k : Sup. : 300	COCO (train) : 36	741.0	50.4	69.1	54.8	—	—	—
ConvNeXt	ConvNeXt-XL	IN-22k : Sup. : 90	COCO (train) : 36	1898.0	55.2	74.2	59.9	—	—	—
Swin	Swin-T	IN-1k : Sup. : 300	COCO (train) : 36	745.0	50.4	69.2	54.7	—	—	—
Swin	Swin-B	IN-1k : Sup. : 300	COCO (train) : 36	982.0	51.9	70.5	56.4	—	—	—
Swin	Swin-B	IN-1k : Sup. : 300	COCO (train) : 50	982.0	52.7	—	—	—	—	—
Swin	Swin-B	IN-22k : Sup. : 90	COCO (train) : 36	982.0	53.0	71.8	57.5	—	—	—
Swin	Swin-B	IN-22k : Sup. : 90	COCO (train) : 50	982.0	54.0	—	—	—	—	—
Swin	Swin-S	IN-1k : Sup. : 300	COCO (train) : 36	838.0	51.9	70.7	56.3	—	—	—
Swin	Swin-L	IN-22k : Sup. : 90	COCO (train) : 36	1382.0	53.9	72.4	58.8	—	—	—
Swin	Swin-L	IN-22k : Sup. : 90	COCO (train) : 50	1382.0	54.8	—	—	—	—	—
InternImage	InternImage-L	IN-22k : Sup. : 90	COCO (train) : 12	1399.0	54.9	74.0	59.8	—	—	—
InternImage	InternImage-L	IN-22k : Sup. : 90	COCO (train) : 36	1399.0	56.1	74.8	60.7	—	—	—
InternImage	InternImage-XL	IN-22k : Sup. : 90	COCO (train) : 12	1782.0	55.3	74.4	60.1	—	—	—
InternImage	InternImage-XL	IN-22k : Sup. : 90	COCO (train) : 36	1782.0	56.2	75.0	61.2	—	—	—
FocalNet	FocalNet-T-LRF	IN-1k : Sup. : 300	COCO (train) : 36	751.0	51.5	70.3	56.0	—	—	—
FocalNet	FocalNet-T-SRF	IN-1k : Sup. : 300	COCO (train) : 36	746.0	51.5	70.1	55.8	—	—	—
CSWin	CSWin-T	IN-1k : Sup. : 300	COCO (train) : 36	757.0	52.5	71.5	57.1	—	—	—
CSWin	CSWin-S	IN-1k : Sup. : 300	COCO (train) : 36	820.0	53.7	72.2	58.4	—	—	—
CSWin	CSWin-B	IN-1k : Sup. : 300	COCO (train) : 36	1004.0	53.9	72.6	58.5	—	—	—
CAFormer	CAFormer-S18	IN-1k : Sup. : 300	COCO (train) : 36	1466.0	52.3	71.3	56.9	—	—	—
CAFormer	CAFormer-S36	IN-1k : Sup. : 300	COCO (train) : 36	1622.0	53.2	72.1	57.7	—	—	—
CAFormer	CAFormer-M36	IN-1k : Sup. : 300	COCO (train) : 36	1840.0	53.8	72.5	58.3	—	—	—
ConvFormer	ConvFormer-S18	IN-1k : Sup. : 300	COCO (train) : 36	1458.0	51.5	70.7	55.8	—	—	—
ConvFormer	ConvFormer-S36	IN-1k : Sup. : 300	COCO (train) : 36	1610.0	52.5	71.1	57.0	—	—	—
ConvFormer	ConvFormer-M36	IN-1k : Sup. : 300	COCO (train) : 36	1824.0	53.0	71.4	57.4	—	—	—
MaxViT	MaxViT-T	IN-1k : Sup. : 300	COCO (train) : 36	475.0	52.1	71.9	56.8	—	—	—
MaxViT	MaxViT-S	IN-1k : Sup. : 300	COCO (train) : 36	595.0	53.1	72.5	58.1	—	—	—
MaxViT	MaxViT-B	IN-1k : Sup. : 300	COCO (train) : 36	856.0	53.4	72.9	58.1	—	—	—
MogaNet	MogaNet-S	IN-1k : Sup. : 300	COCO (train) : 36	750.0	51.6	70.8	56.3	—	—	—
MogaNet	MogaNet-B	IN-1k : Sup. : 300	COCO (train) : 36	851.0	52.6	72.0	57.3	—	—	—
MogaNet	MogaNet-L	IN-1k : Sup. : 300	COCO (train) : 36	974.0	53.3	71.8	57.8	—	—	—
MogaNet	MogaNet-XL	IN-22k : Sup. : 90	COCO (train) : 36	1355.0	56.2	75.0	61.2	—	—	—
UniRepLKNet	UniRepLKNet-T	IN-1k : Sup. : 300	COCO (train) : 36	749.0	51.8	—	—	—	—	—
UniRepLKNet	UniRepLKNet-S	IN-1k : Sup. : 300	COCO (train) : 36	835.0	53.0	—	—	—	—	—
UniRepLKNet	UniRepLKNet-S	IN-22k : Sup. : 90	COCO (train) : 36	835.0	54.3	—	—	—	—	—
UniRepLKNet	UniRepLKNet-B	IN-22k : Sup. : 90	COCO (train) : 36	978.0	54.8	—	—	—	—	—
UniRepLKNet	UniRepLKNet-L	IN-22k : Sup. : 90	COCO (train) : 36	1385.0	55.8	—	—	—	—	—
UniRepLKNet	UniRepLKNet-XL	IN-22k : Sup. : 90	COCO (train) : 36	1952.0	56.4	—	—	—	—	—
SLaK	SLaK-T	IN-1k : Sup. : 300	COCO (train) : 36	None	51.3	70.0	55.7	—	—	—
RepLKNet	RepLKNet-31B	IN-1k : Sup. : 300	COCO (train) : 36	965.0	52.2	—	—	—	—	—
RepLKNet	RepLKNet-31B	IN-22k : Sup. : 90	COCO (train) : 36	965.0	53.0	—	—	—	—	—
RepLKNet	RepLKNet-31L	IN-22k : Sup. : 90	COCO (train) : 36	1321.0	53.9	—	—	—	—	—
RepLKNet	RepLKNet-XL	MegData73M : Sup. : 15	COCO (train) : 36	1958.0	55.5	—	—	—	—	—
Vim	Vim-Ti	IN-1k : Sup. : 300	COCO (train) : 200	None	45.7	63.9	49.6	26.1	49.0	63.2
LocalVim	LocalVim-T	IN-1k : Sup. : 300	COCO (train) : 200	403.0	45.3	66.2	49.1	26.0	49.5	61.7
RMT	RMT-S	IN-1k : Sup. : 300	COCO (train) : 36	741.0	53.2	72.0	57.8	—	—	—
RMT	RMT-B	IN-1k : Sup. : 300	COCO (train) : 36	852.0	54.5	72.8	59.0	—	—	—
DAT++	DAT-T++	IN-1k : Sup. : 300	COCO (train) : 12	771.0	52.2	70.9	56.6	33.9	56.2	68.1
DAT++	DAT-T++	IN-1k : Sup. : 300	COCO (train) : 36	771.0	53.0	71.6	57.7	37.1	56.6	68.6
DAT++	DAT-S++	IN-1k : Sup. : 300	COCO (train) : 36	895.0	54.2	72.7	58.9	38.0	58.3	69.7
DAT++	DAT-B++	IN-1k : Sup. : 300	COCO (train) : 36	1059.0	54.5	73.0	59.4	38.5	58.4	69.8
FAN	FAN-T-Hybrid	IN-1k : Sup. : 300	COCO (train) : 36	None	50.2	—	—	—	—	—
FAN	FAN-S-Hybrid	IN-1k : Sup. : 300	COCO (train) : 36	None	53.3	—	—	—	—	—
FAN	FAN-S-Hybrid	IN-1k : Sup. + TL : 350	COCO (train) : 36	None	53.4	—	—	—	—	—
FAN	FAN-B-Hybrid	IN-1k : Sup. + TL : 350	COCO (train) : 36	None	53.9	—	—	—	—	—
FAN	FAN-L-Hybrid	IN-1k : Sup. : 300	COCO (train) : 36	None	54.1	—	—	—	—	—
FAN	FAN-L-Hybrid	IN-22k : Sup. : 90	COCO (train) : 36	None	55.1	—	—	—	—	—
FAN	FAN-L-Hybrid	IN-1k : Sup. + TL : 350	COCO (train) : 36	None	54.1	—	—	—	—	—
DAT	DAT-T	IN-1k : Sup. : 300	COCO (train) : 12	750.0	49.1	68.2	52.9	31.2	52.4	65.1
DAT	DAT-T	IN-1k : Sup. : 300	COCO (train) : 36	750.0	51.3	70.1	55.8	34.1	54.6	66.9
DAT	DAT-S	IN-1k : Sup. : 300	COCO (train) : 36	857.0	52.7	71.7	57.2	37.3	56.3	68.0
DAT	DAT-B	IN-1k : Sup. : 300	COCO (train) : 36	1003.0	53.0	71.9	57.6	36.0	56.8	69.1
NAT	NAT-M	IN-1k : Sup. : 300	COCO (train) : 36	704.0	50.3	68.9	54.9	—	—	—
NAT	NAT-T	IN-1k : Sup. : 300	COCO (train) : 36	737.0	51.4	70.0	55.9	—	—	—
NAT	NAT-S	IN-1k : Sup. : 300	COCO (train) : 36	809.0	52.0	70.4	56.3	—	—	—
NAT	NAT-B	IN-1k : Sup. : 300	COCO (train) : 36	931.0	52.5	71.1	57.1	—	—	—
SSViT	SSViT-S	IN-1k : Sup. : 300	COCO (train) : 36	745.0	53.8	72.4	58.1	—	—	—
SSViT	SSViT-B	IN-1k : Sup. : 300	COCO (train) : 36	861.0	54.9	73.7	59.7	—	—	—
Iwin Transformer	Iwin-T	IN-1k : Sup. : 300	COCO (train) : 12	747.0	47.2	66.1	51.3	—	—	—
Iwin Transformer	Iwin-T	IN-1k : Sup. : 300	COCO (train) : 36	747.0	49.4	68.4	53.5	—	—	—
Iwin Transformer	Iwin-S	IN-1k : Sup. : 300	COCO (train) : 36	837.0	49.4	68.1	53.3	—	—	—
MA ViT	MA ViT-S	IN-1k : Sup. : 300	COCO (train) : 36	741.0	54.2	72.6	58.6	—	—	—
MA ViT	MA ViT-B	IN-1k : Sup. : 300	COCO (train) : 36	851.0	55.5	74.0	60.4	—	—	—
MA ViT	MA ViT-L	IN-1k : Sup. : 300	COCO (train) : 36	979.0	56.0	74.6	60.9	—	—	—
UniConvNet	UniConvNet-L	IN-22k : Sup. : 90	COCO (train) : 12	1288.0	55.7	74.4	60.4	—	—	—
UniConvNet	UniConvNet-L	IN-22k : Sup. : 90	COCO (train) : 36	1288.0	56.6	75.6	61.8	—	—	—
A2Mamba	A2Mamba-S	IN-1k : Sup. : 300	COCO (train) : 36	762.0	54.0	—	—	—	—	—
A2Mamba	A2Mamba-B	IN-1k : Sup. : 300	COCO (train) : 36	889.0	55.4	—	—	—	—	—
A2Mamba	A2Mamba-L	IN-1k : Sup. : 300	COCO (train) : 36	1027.0	55.6	—	—	—	—	—
CoCA ViT	CoCA ViT-21M	IN-1k : Sup. : 300	COCO (train) : 36	None	51.8	70.5	56.1	—	—	—
CoCA ViT	CoCA ViT-28M	IN-1k : Sup. : 300	COCO (train) : 36	None	52.2	71.0	56.8	—	—	—
HybridNet	HybridNet-T	IN-1k : MAP : 1600	COCO (train) : 36	None	46.4	—	—	—	—	—

COCO (val)

family	model	pretrain	train	gflops	mAP^m	AP^m₅₀	AP^m₇₅	mAP^m_s	mAP^m_m	mAP^m_l
ConvNeXt	ConvNeXt-L	IN-22k : Sup. : 90	COCO (train) : 36	1354.0	47.6	71.3	51.7	—	—	—
ConvNeXt	ConvNeXt-B	IN-1k : Sup. : 300	COCO (train) : 36	964.0	45.6	68.9	49.5	—	—	—
ConvNeXt	ConvNeXt-B	IN-22k : Sup. : 90	COCO (train) : 36	964.0	46.9	70.6	51.3	—	—	—
ConvNeXt	ConvNeXt-S	IN-1k : Sup. : 300	COCO (train) : 36	827.0	45.0	68.4	49.1	—	—	—
ConvNeXt	ConvNeXt-T	IN-1k : Sup. : 300	COCO (train) : 36	741.0	43.7	66.5	47.3	—	—	—
ConvNeXt	ConvNeXt-XL	IN-22k : Sup. : 90	COCO (train) : 36	1898.0	47.7	71.6	52.2	—	—	—
Swin	Swin-T	IN-1k : Sup. : 300	COCO (train) : 36	745.0	43.7	66.6	47.3	—	—	—
Swin	Swin-B	IN-1k : Sup. : 300	COCO (train) : 36	982.0	45.0	68.1	48.9	—	—	—
Swin	Swin-B	IN-1k : Sup. : 300	COCO (train) : 50	982.0	45.5	—	—	—	—	—
Swin	Swin-B	IN-22k : Sup. : 90	COCO (train) : 36	982.0	45.8	69.4	49.7	—	—	—
Swin	Swin-B	IN-22k : Sup. : 90	COCO (train) : 50	982.0	46.5	—	—	—	—	—
Swin	Swin-S	IN-1k : Sup. : 300	COCO (train) : 36	838.0	45.0	68.2	48.8	—	—	—
Swin	Swin-L	IN-22k : Sup. : 90	COCO (train) : 36	1382.0	46.7	70.1	50.8	—	—	—
Swin	Swin-L	IN-22k : Sup. : 90	COCO (train) : 50	1382.0	47.3	—	—	—	—	—
InternImage	InternImage-L	IN-22k : Sup. : 90	COCO (train) : 12	1399.0	47.7	71.4	52.1	—	—	—
InternImage	InternImage-L	IN-22k : Sup. : 90	COCO (train) : 36	1399.0	48.5	72.4	53.0	—	—	—
InternImage	InternImage-XL	IN-22k : Sup. : 90	COCO (train) : 36	1782.0	48.1	71.9	52.4	—	—	—
InternImage	InternImage-XL	IN-22k : Sup. : 90	COCO (train) : 36	1782.0	48.8	72.5	53.4	—	—	—
CSWin	CSWin-T	IN-1k : Sup. : 300	COCO (train) : 36	757.0	45.3	68.8	48.9	—	—	—
CSWin	CSWin-S	IN-1k : Sup. : 300	COCO (train) : 36	820.0	46.4	69.6	50.6	—	—	—
CSWin	CSWin-B	IN-1k : Sup. : 300	COCO (train) : 36	1004.0	46.4	70.0	50.4	—	—	—
CAFormer	CAFormer-S18	IN-1k : Sup. : 300	COCO (train) : 36	1466.0	45.2	68.6	48.8	—	—	—
CAFormer	CAFormer-S36	IN-1k : Sup. : 300	COCO (train) : 36	1622.0	46.0	69.5	49.8	—	—	—
CAFormer	CAFormer-M36	IN-1k : Sup. : 300	COCO (train) : 36	1840.0	46.5	70.1	50.7	—	—	—
ConvFormer	ConvFormer-S18	IN-1k : Sup. : 300	COCO (train) : 36	1458.0	44.6	67.8	48.2	—	—	—
ConvFormer	ConvFormer-S36	IN-1k : Sup. : 300	COCO (train) : 36	1610.0	45.2	68.6	48.8	—	—	—
ConvFormer	ConvFormer-M36	IN-1k : Sup. : 300	COCO (train) : 36	1824.0	45.7	69.2	49.5	—	—	—
MaxViT	MaxViT-T	IN-1k : Sup. : 300	COCO (train) : 36	475.0	44.6	69.1	48.4	—	—	—
MaxViT	MaxViT-S	IN-1k : Sup. : 300	COCO (train) : 36	595.0	45.4	69.8	49.5	—	—	—
MaxViT	MaxViT-B	IN-1k : Sup. : 300	COCO (train) : 36	856.0	45.7	70.3	50.0	—	—	—
MogaNet	MogaNet-S	IN-1k : Sup. : 300	COCO (train) : 36	750.0	45.1	68.7	48.8	—	—	—
MogaNet	MogaNet-B	IN-1k : Sup. : 300	COCO (train) : 36	851.0	46.0	69.6	49.7	—	—	—
MogaNet	MogaNet-L	IN-1k : Sup. : 300	COCO (train) : 36	974.0	46.1	69.2	49.8	—	—	—
MogaNet	MogaNet-XL	IN-22k : Sup. : 90	COCO (train) : 36	1355.0	48.8	72.6	53.3	—	—	—
UniRepLKNet	UniRepLKNet-T	IN-1k : Sup. : 300	COCO (train) : 36	749.0	44.9	—	—	—	—	—
UniRepLKNet	UniRepLKNet-S	IN-1k : Sup. : 300	COCO (train) : 36	835.0	45.9	—	—	—	—	—
UniRepLKNet	UniRepLKNet-S	IN-22k : Sup. : 90	COCO (train) : 36	835.0	47.1	—	—	—	—	—
UniRepLKNet	UniRepLKNet-B	IN-22k : Sup. : 90	COCO (train) : 36	978.0	47.4	—	—	—	—	—
UniRepLKNet	UniRepLKNet-L	IN-22k : Sup. : 90	COCO (train) : 36	1385.0	48.4	—	—	—	—	—
UniRepLKNet	UniRepLKNet-XL	IN-22k : Sup. : 90	COCO (train) : 36	1952.0	49.0	—	—	—	—	—
SLaK	SLaK-T	IN-1k : Sup. : 300	COCO (train) : 36	None	44.3	67.2	48.1	—	—	—
RepLKNet	RepLKNet-31B	IN-1k : Sup. : 300	COCO (train) : 36	965.0	45.2	—	—	—	—	—
RepLKNet	RepLKNet-31B	IN-22k : Sup. : 90	COCO (train) : 36	965.0	46.0	—	—	—	—	—
RepLKNet	RepLKNet-31L	IN-22k : Sup. : 90	COCO (train) : 36	1321.0	46.5	—	—	—	—	—
RepLKNet	RepLKNet-XL	MegData73M : Sup. : 15	COCO (train) : 36	1958.0	48.0	—	—	—	—	—
Vim	Vim-Ti	IN-1k : Sup. : 300	COCO (train) : 200	None	39.2	60.9	41.7	18.2	41.8	60.2
LocalVim	LocalVim-T	IN-1k : Sup. : 300	COCO (train) : 200	403.0	39.9	63.0	42.5	17.7	43.0	60.5
RMT	RMT-S	IN-1k : Sup. : 300	COCO (train) : 36	741.0	46.1	69.8	49.8	—	—	—
RMT	RMT-B	IN-1k : Sup. : 300	COCO (train) : 36	852.0	47.2	70.5	51.4	—	—	—
DAT++	DAT-T++	IN-1k : Sup. : 300	COCO (train) : 12	771.0	45.0	68.1	48.9	25.1	48.5	63.4
DAT++	DAT-T++	IN-1k : Sup. : 300	COCO (train) : 36	771.0	46.0	69.3	50.1	26.7	49.3	64.3
DAT++	DAT-S++	IN-1k : Sup. : 300	COCO (train) : 36	895.0	46.9	70.1	51.3	28.3	50.3	65.8
DAT++	DAT-B++	IN-1k : Sup. : 300	COCO (train) : 36	1059.0	47.0	70.5	51.4	27.9	50.3	65.8
DAT	DAT-T	IN-1k : Sup. : 300	COCO (train) : 12	750.0	42.5	65.4	45.8	25.2	45.9	58.6
DAT	DAT-T	IN-1k : Sup. : 300	COCO (train) : 36	750.0	44.5	67.5	48.1	27.9	47.9	60.3
DAT	DAT-S	IN-1k : Sup. : 300	COCO (train) : 36	857.0	45.5	69.1	49.3	30.2	49.2	60.9
DAT	DAT-B	IN-1k : Sup. : 300	COCO (train) : 36	1003.0	45.8	69.3	49.5	29.2	49.5	61.9
NAT	NAT-M	IN-1k : Sup. : 300	COCO (train) : 36	704.0	43.6	66.4	47.2	—	—	—
NAT	NAT-T	IN-1k : Sup. : 300	COCO (train) : 36	737.0	44.5	67.6	47.9	—	—	—
NAT	NAT-S	IN-1k : Sup. : 300	COCO (train) : 36	809.0	44.9	68.1	48.6	—	—	—
NAT	NAT-B	IN-1k : Sup. : 300	COCO (train) : 36	931.0	45.2	68.6	49.0	—	—	—
SSViT	SSViT-S	IN-1k : Sup. : 300	COCO (train) : 36	745.0	46.6	70.1	50.4	—	—	—
SSViT	SSViT-B	IN-1k : Sup. : 300	COCO (train) : 36	861.0	47.6	71.6	51.5	—	—	—
Iwin Transformer	Iwin-T	IN-1k : Sup. : 300	COCO (train) : 12	747.0	40.9	63.5	44.1	—	—	—
Iwin Transformer	Iwin-T	IN-1k : Sup. : 300	COCO (train) : 36	747.0	42.9	65.8	46.4	—	—	—
Iwin Transformer	Iwin-S	IN-1k : Sup. : 300	COCO (train) : 36	837.0	43.0	65.6	46.4	—	—	—
MA ViT	MA ViT-S	IN-1k : Sup. : 300	COCO (train) : 36	741.0	47.0	70.5	51.1	—	—	—
MA ViT	MA ViT-B	IN-1k : Sup. : 300	COCO (train) : 36	851.0	48.0	71.7	52.5	—	—	—
MA ViT	MA ViT-L	IN-1k : Sup. : 300	COCO (train) : 36	979.0	48.4	72.4	52.9	—	—	—
UniConvNet	UniConvNet-L	IN-22k : Sup. : 90	COCO (train) : 12	1288.0	48.3	71.9	52.9	—	—	—
UniConvNet	UniConvNet-L	IN-22k : Sup. : 90	COCO (train) : 36	1288.0	48.9	73.0	53.4	—	—	—
A2Mamba	A2Mamba-S	IN-1k : Sup. : 300	COCO (train) : 36	762.0	46.6	—	—	—	—	—
A2Mamba	A2Mamba-B	IN-1k : Sup. : 300	COCO (train) : 36	889.0	47.6	—	—	—	—	—
A2Mamba	A2Mamba-L	IN-1k : Sup. : 300	COCO (train) : 36	1027.0	48.1	—	—	—	—	—
CoCA ViT	CoCA ViT-21M	IN-1k : Sup. : 300	COCO (train) : 36	None	44.9	67.8	48.2	—	—	—
CoCA ViT	CoCA ViT-28M	IN-1k : Sup. : 300	COCO (train) : 36	None	45.2	68.9	48.8	—	—	—
HybridNet	HybridNet-T	IN-1k : MAP : 1600	COCO (train) : 36	None	39.8	—	—	—	—	—