Heedless Backbones

CSKAFormer 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
CSKAFormer-S18	28.0	IN-1k : Sup. : 310	— : — : —	4.1	83.4
CSKAFormer-B36	119.0	IN-1k : Sup. : 310	— : — : —	24.2	85.7

model	params (m)	pretrain	finetune	gflops	IN-1k
CSKAFormer-S18	28.0	IN-1k : Sup. : 310	— : — : —	4.1	83.4/—
CSKAFormer-B36	119.0	IN-1k : Sup. : 310	— : — : —	24.2	85.7/—

COCO (val)

model	pretrain	head	train	gflops	mAP^b	AP^b₅₀	AP^b₇₅	mAP^b_s	mAP^b_m	mAP^b_l
CSKAFormer-S18	IN-1k : Sup. : 310	Mask R-CNN	COCO (train) : 36	256.0	48.7	70.7	53.4	—	—	—

COCO (val)

model	pretrain	head	train	gflops	mAP^m	AP^m₅₀	AP^m₇₅	mAP^m_s	mAP^m_m	mAP^m_l
CSKAFormer-S18	IN-1k : Sup. : 310	Mask R-CNN	COCO (train) : 36	256.0	43.8	67.6	47.5	—	—	—