Heedless Backbones

LinGlo 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

Pretrain Method

Classification Resolution

Legend attribute (second)

Select an option

----------

Pretrain Dataset

Pretrain Method

Classification Resolution

No Results

model	params (m)	pretrain	finetune	gflops	IN-1k
LinGlo-b0	3.4	IN-1k : Sup. : 300	— : — : —	None	72.5/—
LinGlo-b1	13.1	IN-1k : Sup. : 300	— : — : —	None	79.7/—
LinGlo-b2	25.4	IN-1k : Sup. : 300	— : — : —	None	82.7/—

COCO (val)

model	pretrain	head	train	gflops	mAP^b	AP^b₅₀	AP^b₇₅	mAP^b_s	mAP^b_m	mAP^b_l
LinGlo-b0	IN-1k : Sup. : 300	RetinaNet	COCO (train) : 12	None	38.0	58.3	40.2	22.8	41.2	49.6
LinGlo-b1	IN-1k : Sup. : 300	RetinaNet	COCO (train) : 12	None	41.5	62.4	44.5	27.1	45.4	53.9
LinGlo-b2	IN-1k : Sup. : 300	RetinaNet	COCO (train) : 12	None	44.7	65.8	47.9	28.0	48.9	57.8

ADE20K (val)

model	pretrain	head	train	gflops	mIoU^ms	pAcc^ms	mAcc^ms	mIoU^ss	pAcc^ss	mAcc^ss
LinGlo-b0	IN-1k : Sup. : 300	Panoptic FPN	ADE20K (train) : 64 : 512	None	—	—	—	37.3	—	—
LinGlo-b1	IN-1k : Sup. : 300	Panoptic FPN	ADE20K (train) : 64 : 512	None	—	—	—	42.5	—	—
LinGlo-b2	IN-1k : Sup. : 300	Panoptic FPN	ADE20K (train) : 64 : 512	None	—	—	—	45.2	—	—