Heedless Backbones

X-ViT 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
X-ViT-T	10.0	IN-1k : Sup. : 400	— : — : —	1.9	78.8
X-ViT-S	21.0	IN-1k : Sup. : 400	— : — : —	3.7	82.0
X-ViT-M	37.0	IN-1k : Sup. : 400	— : — : —	7.0	82.8
X-ViT-M	37.0	IN-1k : Sup. : 400	IN-1k : — : 384	20.5	83.8
X-ViT-B	64.0	IN-1k : Sup. : 400	— : — : —	11.9	83.3
X-ViT-B	64.0	IN-1k : Sup. : 400	IN-1k : — : 384	35.1	84.3

model	params (m)	pretrain	finetune	gflops	IN-1k
X-ViT-T	10.0	IN-1k : Sup. : 400	— : — : —	1.9	78.8/—
X-ViT-S	21.0	IN-1k : Sup. : 400	— : — : —	3.7	82.0/—
X-ViT-M	37.0	IN-1k : Sup. : 400	— : — : —	7.0	82.8/—
X-ViT-M	37.0	IN-1k : Sup. : 400	IN-1k : — : 384	20.5	83.8/—
X-ViT-B	64.0	IN-1k : Sup. : 400	— : — : —	11.9	83.3/—
X-ViT-B	64.0	IN-1k : Sup. : 400	IN-1k : — : 384	35.1	84.3/—

COCO (val)

model	pretrain	head	train	gflops	mAP^b	AP^b₅₀	AP^b₇₅	mAP^b_s	mAP^b_m	mAP^b_l
X-ViT-S	IN-1k : Sup. : 400	Mask R-CNN	COCO (train) : 36	None	44.6	—	—	—	—	—
X-ViT-M	IN-1k : Sup. : 400	Mask R-CNN	COCO (train) : 36	None	46.0	—	—	—	—	—
X-ViT-B	IN-1k : Sup. : 400	Mask R-CNN	COCO (train) : 36	None	45.8	—	—	—	—	—

COCO (val)

model	pretrain	head	train	gflops	mAP^m	AP^m₅₀	AP^m₇₅	mAP^m_s	mAP^m_m	mAP^m_l
X-ViT-S	IN-1k : Sup. : 400	Mask R-CNN	COCO (train) : 36	None	40.4	—	—	—	—	—
X-ViT-M	IN-1k : Sup. : 400	Mask R-CNN	COCO (train) : 36	None	41.0	—	—	—	—	—
X-ViT-B	IN-1k : Sup. : 400	Mask R-CNN	COCO (train) : 36	None	41.2	—	—	—	—	—