Heedless Backbones

U-PVT 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-PVT-Micro	4.3	IN-1k : Sup. : 300	— : — : —	0.57	72.8
U-PVT-Tiny	30.8	IN-1k : Sup. : 300	— : — : —	4.56	82.1
U-PVT-Small	50.5	IN-1k : Sup. : 300	— : — : —	7.33	83.2
U-PVT-Base	91.1	IN-1k : Sup. : 300	— : — : —	12.73	83.4

model	params (m)	pretrain	finetune	gflops	IN-1k
U-PVT-Micro	4.3	IN-1k : Sup. : 300	— : — : —	0.57	72.8/—
U-PVT-Tiny	30.8	IN-1k : Sup. : 300	— : — : —	4.56	82.1/—
U-PVT-Small	50.5	IN-1k : Sup. : 300	— : — : —	7.33	83.2/—
U-PVT-Base	91.1	IN-1k : Sup. : 300	— : — : —	12.73	83.4/—

COCO (val)

model	pretrain	head	train	gflops	mAP^b	AP^b₅₀	AP^b₇₅	mAP^b_s	mAP^b_m	mAP^b_l
U-PVT-Micro	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	None	35.9	—	—	21.2	38.4	47.2
U-PVT-Tiny	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	None	44.2	—	—	27.5	47.4	59.1
U-PVT-Small	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	None	46.1	—	—	28.8	49.3	61.2
U-PVT-Base	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	None	46.4	—	—	29.0	49.8	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-PVT-Micro	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	None	34.2	—	—	16.8	36.1	50.2
U-PVT-Tiny	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	None	40.6	—	—	21.1	43.4	59.5
U-PVT-Small	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	None	41.9	—	—	21.9	44.6	61.2
U-PVT-Base	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	None	42.3	—	—	22.3	45.1	61.8