Heedless Backbones

ResT 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
ResT-Lite	10.49	IN-1k : Sup. : 300	— : — : —	1.4	77.2
ResT-Small	13.66	IN-1k : Sup. : 300	— : — : —	1.94	79.6
ResT-Base	30.28	IN-1k : Sup. : 300	— : — : —	4.26	81.6
ResT-Large	51.63	IN-1k : Sup. : 300	— : — : —	7.91	83.6

model	params (m)	pretrain	finetune	gflops	IN-1k
ResT-Lite	10.49	IN-1k : Sup. : 300	— : — : —	1.4	77.2/93.7
ResT-Small	13.66	IN-1k : Sup. : 300	— : — : —	1.94	79.6/94.9
ResT-Base	30.28	IN-1k : Sup. : 300	— : — : —	4.26	81.6/95.7
ResT-Large	51.63	IN-1k : Sup. : 300	— : — : —	7.91	83.6/96.3

COCO (val)

model	pretrain	head	train	gflops	mAP^b	AP^b₅₀	AP^b₇₅	mAP^b_s	mAP^b_m	mAP^b_l
ResT-Small	IN-1k : Sup. : 300	RetinaNet	COCO (train) : 12	None	40.3	61.3	42.7	25.7	43.7	51.2
ResT-Small	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	None	39.6	62.9	42.3	—	—	—
ResT-Base	IN-1k : Sup. : 300	RetinaNet	COCO (train) : 12	None	42.0	63.2	44.8	29.1	45.3	53.3
ResT-Base	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	None	41.6	64.9	45.1	—	—	—
ResT-Large	IN-1k : Sup. : 300	RetinaNet	COCO (train) : 12	None	44.8	66.1	48.0	28.3	48.7	60.3

COCO (val)

model	pretrain	head	train	gflops	mAP^m	AP^m₅₀	AP^m₇₅	mAP^m_s	mAP^m_m	mAP^m_l
ResT-Small	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	None	37.2	59.8	39.7	—	—	—
ResT-Base	IN-1k : Sup. : 300	Mask R-CNN	COCO (train) : 12	None	38.7	61.6	41.4	—	—	—