Heedless Backbones

RandFormer 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

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

pretrain dataset

Select an option

---------

JFT-3B

ImageNet-1k

ImageNet-22k

JFT-300M

pretrain method

Select an option

----------

Supervised

FCMAE

MAE

CL

Legend

Legend attribute

Select an option

Family

Pretrain Dataset

Pretrain Method

Classification Resolution

Legend attribute (second)

Select an option

----------

Family

Pretrain Method

Classification Resolution

model	params (m)	pretrain	finetune	GFLOPs	Top-1
RandFormer-S12	12.1	IN-1k : Sup. : 300	— : — : —	1.9	76.6
RandFormer-S24	21.8	IN-1k : Sup. : 300	— : — : —	3.5	78.8
RandFormer-S36	31.5	IN-1k : Sup. : 300	— : — : —	5.2	79.5
RandFormer-M36	56.8	IN-1k : Sup. : 300	— : — : —	9.0	81.2
RandFormer-M48	74.2	IN-1k : Sup. : 300	— : — : —	11.9	81.4

model	params (m)	pretrain	finetune	gflops	IN-1k
RandFormer-S12	12.1	IN-1k : Sup. : 300	— : — : —	1.9	76.6/—
RandFormer-S24	21.8	IN-1k : Sup. : 300	— : — : —	3.5	78.8/—
RandFormer-S36	31.5	IN-1k : Sup. : 300	— : — : —	5.2	79.5/—
RandFormer-M36	56.8	IN-1k : Sup. : 300	— : — : —	9.0	81.2/—
RandFormer-M48	74.2	IN-1k : Sup. : 300	— : — : —	11.9	81.4/—