Heedless Backbones

CPolyNeXt 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
CPolyNeXt-T	6.4	IN-1k : Sup. : 300	— : — : —	1.2	80.2
CPolyNeXt-S	26.0	IN-1k : Sup. : 300	— : — : —	4.8	83.9
CPolyNeXt-B	40.0	IN-1k : Sup. : 300	— : — : —	8.5	84.7
CPolyNeXt-L	57.0	IN-1k : Sup. : 300	— : — : —	12.6	84.9
CPolyNeXt-T BN	6.4	IN-1k : Sup. : 300	— : — : —	1.2	78.3
CPolyNeXt-S BN	26.0	IN-1k : Sup. : 300	— : — : —	4.8	82.7

model	params (m)	pretrain	finetune	gflops	IN-1k	IN-R	IN-A	IN-C↓	IN-Sketch
CPolyNeXt-T	6.4	IN-1k : Sup. : 300	— : — : —	1.2	80.2/—	—/—	—/—	—/—	—/—
CPolyNeXt-S	26.0	IN-1k : Sup. : 300	— : — : —	4.8	83.9/—	49.4/—	35.1/—	47.9/—	37.8/—
CPolyNeXt-B	40.0	IN-1k : Sup. : 300	— : — : —	8.5	84.7/—	52.0/—	42.8/—	44.5/—	40.0/—
CPolyNeXt-L	57.0	IN-1k : Sup. : 300	— : — : —	12.6	84.9/—	54.5/—	48.3/—	42.5/—	41.8/—
CPolyNeXt-T BN	6.4	IN-1k : Sup. : 300	— : — : —	1.2	78.3/—	—/—	—/—	—/—	—/—
CPolyNeXt-S BN	26.0	IN-1k : Sup. : 300	— : — : —	4.8	82.7/—	—/—	—/—	—/—	—/—

ADE20K (val)

model	pretrain	head	train	gflops	mIoU^ms	pAcc^ms	mAcc^ms	mIoU^ss	pAcc^ss	mAcc^ss
CPolyNeXt-S	IN-1k : Sup. : 300	UPerNet	ADE20K (train) : 128 : 512	941.0	—	—	—	50.6	—	—