Heedless Backbones

U-DWConv 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-DWConv-Micro	4.4	IN-1k : Sup. : 300	— : — : —	0.65	75.1
U-DWConv-Tiny	31.9	IN-1k : Sup. : 300	— : — : —	5.01	82.2
U-DWConv-Small	54.4	IN-1k : Sup. : 300	— : — : —	9.4	83.1
U-DWConv-Base	95.8	IN-1k : Sup. : 300	— : — : —	16.64	83.7

model	params (m)	pretrain	finetune	gflops	IN-1k
U-DWConv-Micro	4.4	IN-1k : Sup. : 300	— : — : —	0.65	75.1/—
U-DWConv-Tiny	31.9	IN-1k : Sup. : 300	— : — : —	5.01	82.2/—
U-DWConv-Small	54.4	IN-1k : Sup. : 300	— : — : —	9.4	83.1/—
U-DWConv-Base	95.8	IN-1k : Sup. : 300	— : — : —	16.64	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-DWConv-Micro	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	None	39.2	—	—	23.0	42.6	51.0
U-DWConv-Tiny	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	None	44.3	—	—	27.8	48.0	57.5
U-DWConv-Small	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	None	45.6	—	—	28.5	49.8	59.8
U-DWConv-Base	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	None	46.7	—	—	30.2	50.3	61.4

COCO (val)

model	pretrain	head	train	gflops	mAP^m	AP^m₅₀	AP^m₇₅	mAP^m_s	mAP^m_m	mAP^m_l
U-DWConv-Micro	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	None	36.4	—	—	17.8	39.2	52.7
U-DWConv-Tiny	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	None	40.5	—	—	20.7	43.9	58.6
U-DWConv-Small	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	None	41.2	—	—	21.9	44.7	59.4
U-DWConv-Base	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	None	42.2	—	—	22.8	45.1	60.7