Heedless Backbones

PVT (SPM) 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
PVT-Tiny (SPM)	14.0	IN-1k : Sup. : 300	— : — : —	2.7	79.5

model	params (m)	pretrain	finetune	gflops	IN-1k
PVT-Tiny (SPM)	14.0	IN-1k : Sup. : 300	— : — : —	2.7	79.5/—
PVT-Small (SPM)	25.3	IN-1k : Sup. : 300	— : — : —	None	81.7/—
PVT-Medium (SPM)	45.0	IN-1k : Sup. : 300	— : — : —	None	81.9/—

COCO (val)

model	pretrain	head	train	gflops	mAP^b	AP^b₅₀	AP^b₇₅	mAP^b_s	mAP^b_m	mAP^b_l
PVT-Tiny (SPM)	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	None	40.8	63.4	44.3	24.9	44.0	54.0
PVT-Small (SPM)	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	None	43.0	65.4	46.7	25.5	46.2	57.6
PVT-Medium (SPM)	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	None	43.3	64.9	47.6	25.8	46.4	58.3

COCO (val)

model	pretrain	head	train	gflops	mAP^m	AP^m₅₀	AP^m₇₅	mAP^m_s	mAP^m_m	mAP^m_l
PVT-Tiny (SPM)	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	None	38.0	60.4	40.6	—	—	—
PVT-Small (SPM)	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	None	39.6	62.3	42.4	—	—	—
PVT-Medium (SPM)	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	None	39.4	61.7	42.2	—	—	—

ADE20K (val)

model	pretrain	head	train	gflops	mIoU^ms	pAcc^ms	mAcc^ms	mIoU^ss	pAcc^ss	mAcc^ss
PVT-Tiny (SPM)	IN-1k : Sup. : 300	Panoptic FPN	ADE20K (train) : 32 : 512	None	—	—	—	41.5	—	—
PVT-Small (SPM)	IN-1k : Sup. : 300	Panoptic FPN	ADE20K (train) : 32 : 512	None	—	—	—	45.9	—	—
PVT-Medium (SPM)	IN-1k : Sup. : 300	Panoptic FPN	ADE20K (train) : 32 : 512	None	—	—	—	45.3	—	—