Heedless Backbones

SLaK 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

---------

COCO (val)

COCO (test)

PASCAL VOC 2007 (val)

PASCAL VOC 2007 (test)

metric

Select an option

----------

mAP

AP₅₀

AP₇₅

mAP_s

mAP_m

mAP_l

GFLOPs

head

Select an option

---------

Mask R-CNN

Cascade Mask R-CNN

RetinaNet

DINO

HTC++

HTC

FCOS

Faster R-CNN

axis

Select an option

Results

Parameters (M)

Images / Second

GFLOPs

Publication Date

Filters

pretrain dataset

Select an option

---------

MegData73M

JFT-3B

JFT-300M

ImageNet-1k

ImageNet-22k

pretrain method

Select an option

----------

Supervised

Sup. + TL

FCMAE

MAE

CL

Legend

Legend attribute

Select an option

Family

Pretrain Dataset

Instance Head

Instance Training Epochs

Legend attribute (second)

Select an option

----------

Family

Pretrain Method

Instance Head

Instance Training Epochs

No Results

model	params (m)	pretrain	finetune	gflops	IN-1k
SLaK-T	30.0	IN-1k : Sup. : 300	— : — : —	5.0	82.5/—
SLaK-S	55.0	IN-1k : Sup. : 300	— : — : —	9.8	83.8/—
SLaK-B	95.0	IN-1k : Sup. : 300	— : — : —	17.1	84.0/—
SLaK-B	95.0	IN-1k : Sup. : 300	IN-1k : 30 : 384	50.3	85.5/—

PASCAL VOC 2007 (test)

model	pretrain	head	train	gflops	mAP^b	AP^b₅₀	AP^b₇₅	mAP^b_s	mAP^b_m	mAP^b_l
SLaK-T	IN-1k : Sup. : 300	Faster R-CNN	PASCAL VOC 2007 (train + val) : 36	205.0	82.7	—	—	—	—	—

COCO (val)

model	pretrain	head	train	gflops	mAP^b	AP^b₅₀	AP^b₇₅	mAP^b_s	mAP^b_m	mAP^b_l
SLaK-T	IN-1k : Sup. : 300	Cascade Mask R-CNN	COCO (train) : 36	None	51.3	70.0	55.7	—	—	—

COCO (val)

model	pretrain	head	train	gflops	mAP^m	AP^m₅₀	AP^m₇₅	mAP^m_s	mAP^m_m	mAP^m_l
SLaK-T	IN-1k : Sup. : 300	Cascade Mask R-CNN	COCO (train) : 36	None	44.3	67.2	48.1	—	—	—

ADE20K (val)

model	pretrain	head	train	gflops	mIoU^ms	pAcc^ms	mAcc^ms	mIoU^ss	pAcc^ss	mAcc^ss
SLaK-T	IN-1k : Sup. : 300	UPerNet	ADE20K (train) : 128 : 512	936.0	—	—	—	47.6	—	—
SLaK-S	IN-1k : Sup. : 300	UPerNet	ADE20K (train) : 128 : 512	1028.0	—	—	—	49.4	—	—
SLaK-B	IN-1k : Sup. : 300	UPerNet	ADE20K (train) : 128 : 512	1172.0	—	—	—	50.2	—	—