Heedless Backbones

DeBiFormer 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
DeBiFormer-T	21.4	IN-1k : Sup. : 300	— : — : —	2.6	81.9
DeBiFormer-S	44.0	IN-1k : Sup. : 300	— : — : —	5.4	83.9
DeBiFormer-B	77.0	IN-1k : Sup. : 300	— : — : —	11.8	84.4

model	params (m)	pretrain	finetune	gflops	IN-1k
DeBiFormer-T	21.4	IN-1k : Sup. : 300	— : — : —	2.6	81.9/—
DeBiFormer-S	44.0	IN-1k : Sup. : 300	— : — : —	5.4	83.9/—
DeBiFormer-B	77.0	IN-1k : Sup. : 300	— : — : —	11.8	84.4/—

COCO (val)

model	pretrain	head	train	gflops	mAP^b	AP^b₅₀	AP^b₇₅	mAP^b_s	mAP^b_m	mAP^b_l
DeBiFormer-S	IN-1k : Sup. : 300	RetinaNet	COCO (train) : 12	None	45.6	66.6	48.9	28.7	49.3	61.6
DeBiFormer-S	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	None	47.5	69.7	52.1	—	—	—
DeBiFormer-B	IN-1k : Sup. : 300	RetinaNet	COCO (train) : 12	None	47.1	68.2	50.2	30.3	51.1	63.0
DeBiFormer-B	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	None	48.5	70.2	53.3	—	—	—

COCO (val)

model	pretrain	head	train	gflops	mAP^m	AP^m₅₀	AP^m₇₅	mAP^m_s	mAP^m_m	mAP^m_l
DeBiFormer-S	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	None	42.5	66.2	45.7	—	—	—
DeBiFormer-B	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	None	43.2	67.2	46.4	—	—	—

ADE20K (val)

model	pretrain	head	train	gflops	mIoU^ms	pAcc^ms	mAcc^ms	mIoU^ss	pAcc^ss	mAcc^ss
DeBiFormer-S	IN-1k : Sup. : 300	Panoptic FPN	ADE20K (train) : 128 : 512	None	—	—	—	49.2	—	—
DeBiFormer-S	IN-1k : Sup. : 300	UPerNet	ADE20K (train) : 128 : 512	None	—	—	—	50.0	—	—
DeBiFormer-B	IN-1k : Sup. : 300	Panoptic FPN	ADE20K (train) : 128 : 512	None	—	—	—	50.6	—	—
DeBiFormer-B	IN-1k : Sup. : 300	UPerNet	ADE20K (train) : 128 : 512	None	52.0	—	—	51.4	—	—