Heedless Backbones

LiSA-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
LiSA-PVT-T	12.16	IN-1k : Sup. : 300	— : — : —	2.12	78.53
LiSA-PVT-S	21.69	IN-1k : Sup. : 300	— : — : —	4.18	81.96

model	params (m)	pretrain	finetune	gflops	IN-1k
LiSA-PVT-T	12.16	IN-1k : Sup. : 300	— : — : —	2.12	78.53/—
LiSA-PVT-S	21.69	IN-1k : Sup. : 300	— : — : —	4.18	81.96/—

COCO (val)

model	pretrain	head	train	gflops	mAP^b	AP^b₅₀	AP^b₇₅	mAP^b_s	mAP^b_m	mAP^b_l
LiSA-PVT-T	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	245.0	40.5	62.9	44.1	—	—	—

COCO (val)

model	pretrain	head	train	gflops	mAP^m	AP^m₅₀	AP^m₇₅	mAP^m_s	mAP^m_m	mAP^m_l
LiSA-PVT-T	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	245.0	37.6	59.7	40.2	—	—	—

ADE20K (val)

model	pretrain	head	train	gflops	mIoU^ms	pAcc^ms	mAcc^ms	mIoU^ss	pAcc^ss	mAcc^ss
LiSA-PVT-T	IN-1k : Sup. : 300	Panoptic FPN	ADE20K (train) : 64 : 512	170.0	—	—	—	40.85	—	51.75