Heedless Backbones

RepNeXt 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
RepNeXt-M0	2.3	IN-1k : Sup. : 300	— : — : —	0.4	74.2/—
RepNeXt-M0	2.3	IN-1k : Sup. : 300	— : — : —	0.4	72.6/—
RepNeXt-M1	4.8	IN-1k : Sup. : 300	— : — : —	0.8	78.8/—
RepNeXt-M1	4.8	IN-1k : Sup. : 300	— : — : —	0.8	77.5/—
RepNeXt-M2	6.5	IN-1k : Sup. : 300	— : — : —	1.1	80.1/—
RepNeXt-M2	6.5	IN-1k : Sup. : 300	— : — : —	1.1	78.9/—
RepNeXt-M3	7.8	IN-1k : Sup. : 300	— : — : —	1.3	80.7/—
RepNeXt-M3	7.8	IN-1k : Sup. : 300	— : — : —	1.3	79.4/—
RepNeXt-M4	13.3	IN-1k : Sup. : 300	— : — : —	2.3	82.3/—
RepNeXt-M4	13.3	IN-1k : Sup. : 300	— : — : —	2.3	81.2/—
RepNeXt-M5	21.7	IN-1k : Sup. : 300	— : — : —	4.5	83.3/—
RepNeXt-M5	21.7	IN-1k : Sup. : 300	— : — : —	4.5	82.4/—

COCO (val)

model	pretrain	head	train	gflops	mAP^b	AP^b₅₀	AP^b₇₅	mAP^b_s	mAP^b_m	mAP^b_l
RepNeXt-M3	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	None	40.8	62.4	44.7	—	—	—
RepNeXt-M4	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	None	42.9	64.4	47.2	—	—	—
RepNeXt-M5	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	None	44.7	66.0	49.2	—	—	—

COCO (val)

model	pretrain	head	train	gflops	mAP^m	AP^m₅₀	AP^m₇₅	mAP^m_s	mAP^m_m	mAP^m_l
RepNeXt-M3	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	None	37.8	59.5	40.6	—	—	—
RepNeXt-M4	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	None	39.1	61.7	41.7	—	—	—
RepNeXt-M5	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	None	40.7	63.5	43.6	—	—	—

ADE20K (val)

model	pretrain	head	train	gflops	mIoU^ms	pAcc^ms	mAcc^ms	mIoU^ss	pAcc^ss	mAcc^ss
RepNeXt-M3	IN-1k : Sup. : 300	Panoptic FPN	ADE20K (train) : 64 : 512	None	—	—	—	40.6	—	—
RepNeXt-M4	IN-1k : Sup. : 300	Panoptic FPN	ADE20K (train) : 64 : 512	None	—	—	—	43.3	—	—
RepNeXt-M5	IN-1k : Sup. : 300	Panoptic FPN	ADE20K (train) : 64 : 512	None	—	—	—	45.0	—	—