Heedless Backbones

CE-CSWin 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

pretrain dataset

Select an option

---------

ImageNet-1k

ImageNet-22k

JFT-300M

JFT-3B

MegData73M

pretrain method

Select an option

----------

Supervised

Sup. + TL

FCMAE

MAE

CL

MAP

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
CE-CSWin-T	21.6	IN-1k : Sup. : 300	— : — : —	4.2	83.6
CE-CSWin-S	33.9	IN-1k : Sup. : 300	— : — : —	6.6	84.1
CE-CSWin-B	75.8	IN-1k : Sup. : 300	— : — : —	14.7	84.7

model	params (m)	pretrain	finetune	gflops	IN-1k
CE-CSWin-T	21.6	IN-1k : Sup. : 300	— : — : —	4.2	83.6/—
CE-CSWin-S	33.9	IN-1k : Sup. : 300	— : — : —	6.6	84.1/—
CE-CSWin-B	75.8	IN-1k : Sup. : 300	— : — : —	14.7	84.7/—