Heedless Backbones

InceptionNeXt 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

---------

Cityscapes (val)

Cityscapes (test)

ADE20K (val)

ADE20K (test)

PASCAL VOC 2007 (val)

PASCAL VOC 2007 (test)

metric

Select an option

mIoU^ms

pAcc^ms

mAcc^ms

mIoU^ss

pAcc^ss

mAcc^ss

GFLOPs

head

Select an option

---------

UPerNet

Mask2Former

Panoptic FPN

SETR

resolution

Select an option

----------

512x2048

640x2560

axis

Select an option

Results

Parameters (M)

Images / Second

GFLOPs

Publication Date

Filters

Legend

Legend attribute

Select an option

Family

Pretrain Dataset

Semantic Segmentation Head

Semantic Segmentation Resolution

Semantic Segmentation Training Epochs

Legend attribute (second)

Select an option

----------

Family

Pretrain Method

Semantic Segmentation Head

Semantic Segmentation Resolution

Semantic Segmentation Training Epochs

model	params (m)	pretrain	head	train	GFLOPs	mIoU^ms
InceptionNeXt-T	28.1	IN-1k : Sup. : 300	UPerNet	ADE20K (train) : 128 : 512	933.0	47.9
InceptionNeXt-S	49.4	IN-1k : Sup. : 300	UPerNet	ADE20K (train) : 128 : 512	1020.0	50.0
InceptionNeXt-B	86.7	IN-1k : Sup. : 300	UPerNet	ADE20K (train) : 128 : 512	1159.0	50.6

model	params (m)	pretrain	finetune	gflops	IN-1k
InceptionNeXt-A	4.2	IN-1k : Sup. : 450	— : — : —	0.51	75.3/—
InceptionNeXt-T	28.1	IN-1k : Sup. : 300	— : — : —	4.2	82.3/—
InceptionNeXt-S	49.4	IN-1k : Sup. : 300	— : — : —	8.4	83.5/—
InceptionNeXt-B	86.7	IN-1k : Sup. : 300	— : — : —	14.9	84.0/—
InceptionNeXt-B	86.7	IN-1k : Sup. : 300	IN-1k : 30 : 384	43.6	85.2/—

ADE20K (val)

model	pretrain	head	train	gflops	mIoU^ms	pAcc^ms	mAcc^ms	mIoU^ss	pAcc^ss	mAcc^ss
InceptionNeXt-T	IN-1k : Sup. : 300	UPerNet	ADE20K (train) : 128 : 512	933.0	47.9	—	—	—	—	—
InceptionNeXt-T	IN-1k : Sup. : 300	Panoptic FPN	ADE20K (train) : 64 : 512	44.0	—	—	—	43.1	—	—
InceptionNeXt-S	IN-1k : Sup. : 300	UPerNet	ADE20K (train) : 128 : 512	1020.0	50.0	—	—	—	—	—
InceptionNeXt-S	IN-1k : Sup. : 300	Panoptic FPN	ADE20K (train) : 64 : 512	65.0	—	—	—	45.6	—	—
InceptionNeXt-B	IN-1k : Sup. : 300	UPerNet	ADE20K (train) : 128 : 512	1159.0	50.6	—	—	—	—	—
InceptionNeXt-B	IN-1k : Sup. : 300	Panoptic FPN	ADE20K (train) : 64 : 512	100.0	—	—	—	46.4	—	—