Heedless Backbones

FViT 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
FViT-Tiny	11.28	IN-1k : Sup. : 300	— : — : —	1.94	79.1
FViT-Small	23.59	IN-1k : Sup. : 300	— : — : —	3.98	82.3
FViT-Base	43.15	IN-1k : Sup. : 300	— : — : —	7.21	83.4
FViT-Large	60.15	IN-1k : Sup. : 300	— : — : —	10.18	83.8

model	params (m)	pretrain	finetune	gflops	IN-1k
FViT-Tiny	11.28	IN-1k : Sup. : 300	— : — : —	1.94	79.1/—
FViT-Small	23.59	IN-1k : Sup. : 300	— : — : —	3.98	82.3/—
FViT-Base	43.15	IN-1k : Sup. : 300	— : — : —	7.21	83.4/—
FViT-Large	60.15	IN-1k : Sup. : 300	— : — : —	10.18	83.8/—

COCO (val)

model	pretrain	head	train	gflops	mAP^b	AP^b₅₀	AP^b₇₅	mAP^b_s	mAP^b_m	mAP^b_l
FViT-Small	IN-1k : Sup. : 300	RetinaNet	COCO (train) : 12	None	44.7	65.8	47.9	28.3	48.8	59.5
FViT-Small	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	None	45.6	68.1	50.0	—	—	—
FViT-Base	IN-1k : Sup. : 300	RetinaNet	COCO (train) : 12	None	46.4	68.3	49.6	30.2	50.7	61.8
FViT-Base	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	None	47.3	69.6	52.2	—	—	—

COCO (val)

model	pretrain	head	train	gflops	mAP^m	AP^m₅₀	AP^m₇₅	mAP^m_s	mAP^m_m	mAP^m_l
FViT-Small	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	None	41.5	64.9	44.7	—	—	—
FViT-Base	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	None	42.9	66.5	46.3	—	—	—

ADE20K (val)

model	pretrain	head	train	gflops	mIoU^ms	pAcc^ms	mAcc^ms	mIoU^ss	pAcc^ss	mAcc^ss
FViT-Small	IN-1k : Sup. : 300	Panoptic FPN	ADE20K (train) : 64 : 512	46.2	—	—	—	46.1	—	—
FViT-Base	IN-1k : Sup. : 300	Panoptic FPN	ADE20K (train) : 64 : 512	62.7	—	—	—	47.9	—	—