Heedless Backbones

MHLA-DeiT 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
MHLA-DeiT-T	5.7	IN-1k : Sup. : 300	— : — : —	1.1	75.8
MHLA-DeiT-S	22.0	IN-1k : Sup. : 300	— : — : —	4.2	81.0

model	params (m)	pretrain	finetune	gflops	IN-1k
MHLA-DeiT-T	5.7	IN-1k : Sup. : 300	— : — : —	1.1	75.8/—
MHLA-DeiT-S	22.0	IN-1k : Sup. : 300	— : — : —	4.2	81.0/—