Heedless Backbones

APolyNeXt 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

---------

ImageNet-1k

ImageNet-A

ImageNet-R

ImageNet-Sketch

ImageNet-C

ImageNet-C-bar

ImageNet-V2

ImageNet-ReaL

PASCAL VOC 2007 (val)

PASCAL VOC 2007 (test)

metric

Select an option

----------

Top-1

Top-5

GFLOPs

resolution

Select an option

----------

224x224

384x384

512x512

axis

Select an option

Results

Parameters (M)

Images / Second

GFLOPs

Publication Date

Filters

Legend

Legend attribute

Select an option

Family

Pretrain Dataset

Classification Resolution

Legend attribute (second)

Select an option

----------

Family

Pretrain Method

Classification Resolution

model	params (m)	pretrain	finetune	GFLOPs	Top-1
APolyNeXt-T	6.5	IN-1k : Sup. : 300	— : — : —	1.3	80.9
APolyNeXt-S	26.0	IN-1k : Sup. : 300	— : — : —	5.3	84.3
APolyNeXt-B	41.0	IN-1k : Sup. : 300	— : — : —	9.3	84.9
APolyNeXt-L	57.0	IN-1k : Sup. : 300	— : — : —	13.3	85.2
APolyNeXt-T BN	6.5	IN-1k : Sup. : 300	— : — : —	1.3	78.0

model	params (m)	pretrain	finetune	gflops	IN-1k	IN-R	IN-A	IN-C↓	IN-Sketch
APolyNeXt-T	6.5	IN-1k : Sup. : 300	— : — : —	1.3	80.9/—	—/—	—/—	—/—	—/—
APolyNeXt-S	26.0	IN-1k : Sup. : 300	— : — : —	5.3	84.3/—	49.7/—	39.6/—	45.0/—	37.5/—
APolyNeXt-B	41.0	IN-1k : Sup. : 300	— : — : —	9.3	84.9/—	52.9/—	45.5/—	42.7/—	41.1/—
APolyNeXt-L	57.0	IN-1k : Sup. : 300	— : — : —	13.3	85.2/—	54.0/—	49.2/—	42.9/—	41.8/—
APolyNeXt-T BN	6.5	IN-1k : Sup. : 300	— : — : —	1.3	78.0/—	—/—	—/—	—/—	—/—

ADE20K (val)

model	pretrain	head	train	gflops	mIoU^ms	pAcc^ms	mAcc^ms	mIoU^ss	pAcc^ss	mAcc^ss
APolyNeXt-S	IN-1k : Sup. : 300	UPerNet	ADE20K (train) : 128 : 512	1121.0	—	—	—	49.9	—	—