Heedless Backbones

Sparse R-CNN

Paper | GitHub

axis

Select an option

Results

Parameters (M)

Images / Second

Publication Date

task

Select an option

---------

Object Detection

dataset

Select an option

---------

COCO (val)

COCO (test)

PASCAL VOC 2007 (val)

PASCAL VOC 2007 (test)

metric

Select an option

----------

mAP

AP₅₀

AP₇₅

mAP_s

mAP_m

mAP_l

GFLOPs

axis

Select an option

Results

Parameters (M)

Images / Second

GFLOPs

Publication Date

Filters

Legend

Legend attribute

Select an option

Family

Pretrain Dataset

Pretrain Method

Instance Head

Instance Training Epochs

Legend attribute (second)

Select an option

----------

Pretrain Dataset

Pretrain Method

Instance Head

Instance Training Epochs

family	model	params (m)	pretrain	head	train	GFLOPs	mAP
Swin	Swin-T	29.0	IN-1k : Sup. : 300	Sparse R-CNN	COCO (train) : 36	172.0	47.9
FocalNet	FocalNet-T-LRF	28.6	IN-1k : Sup. : 300	Sparse R-CNN	COCO (train) : 36	178.0	49.9
SMT	SMT-S	20.5	IN-1k : Sup. : 300	Sparse R-CNN	COCO (train) : 36	171.0	50.2

COCO (val)

family	model	pretrain	train	gflops	mAP^b	AP^b₅₀	AP^b₇₅	mAP^b_s	mAP^b_m	mAP^b_l
Swin	Swin-T	IN-1k : Sup. : 300	COCO (train) : 36	172.0	47.9	67.3	52.3	—	—	—
FocalNet	FocalNet-T-LRF	IN-1k : Sup. : 300	COCO (train) : 36	178.0	49.9	69.6	54.4	—	—	—
SMT	SMT-S	IN-1k : Sup. : 300	COCO (train) : 36	171.0	50.2	69.8	54.7	—	—	—