Heedless Backbones

U-Swin 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
U-Swin-Micro	4.4	IN-1k : Sup. : 300	— : — : —	0.71	74.4
U-Swin-Tiny	31.5	IN-1k : Sup. : 300	— : — : —	4.91	82.3
U-Swin-Small	52.9	IN-1k : Sup. : 300	— : — : —	9.18	83.3
U-Swin-Base	93.4	IN-1k : Sup. : 300	— : — : —	16.18	83.7

model	params (m)	pretrain	finetune	gflops	IN-1k
U-Swin-Micro	4.4	IN-1k : Sup. : 300	— : — : —	0.71	74.4/—
U-Swin-Tiny	31.5	IN-1k : Sup. : 300	— : — : —	4.91	82.3/—
U-Swin-Small	52.9	IN-1k : Sup. : 300	— : — : —	9.18	83.3/—
U-Swin-Base	93.4	IN-1k : Sup. : 300	— : — : —	16.18	83.7/—

COCO (val)

model	pretrain	head	train	gflops	mAP^b	AP^b₅₀	AP^b₇₅	mAP^b_s	mAP^b_m	mAP^b_l
U-Swin-Micro	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	None	36.6	—	—	22.3	39.1	48.0
U-Swin-Tiny	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	None	44.3	—	—	28.0	47.5	57.8
U-Swin-Small	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	None	46.4	—	—	28.2	50.0	61.5
U-Swin-Base	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	None	47.0	—	—	30.8	50.6	62.2

COCO (val)

model	pretrain	head	train	gflops	mAP^m	AP^m₅₀	AP^m₇₅	mAP^m_s	mAP^m_m	mAP^m_l
U-Swin-Micro	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	None	34.6	—	—	17.2	36.7	50.1
U-Swin-Tiny	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	None	40.5	—	—	21.6	43.0	58.2
U-Swin-Small	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	None	42.1	—	—	21.8	45.2	60.7
U-Swin-Base	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	None	42.2	—	—	23.5	45.1	61.7