Researching | Backbone Network for Object Detection Task

Laser & Optoelectronics Progress, Volume. 57, Issue 4, 041021(2020)

Backbone Network for Object Detection Task

Yalin Song^* and Yanwei Pang

Author Affiliations

School of Electrical and Information Engineering, Tianjin University, Tianjin 300072, China

show less

Abstract Get PDF(in Chinese)

Figures&Tables (12)

References (28)

Paper Information

Figures & Tables(12)

Fig. 1. Network architecture

Download full size

Fig. 2. Initial module

Download full size

Fig. 3. Feature fusion module

Download full size

Fig. 4. Mix down-sampling module

Download full size

Fig. 5. Prediction modules. (a) Plain prediction module; (b) dense prediction module

Download full size

Fig. 6. Qualitative detection results

Download full size

Table 1. Comparison of different initial modules
View table
Table 1. Comparison of different initial modules
Initial block M_AP /% Speed /(frame·s^-1)
7×7-s2 79.9 85
3×3 conv-s1,3×3conv-s1,3×3 conv-s2, 80.7 85
3×3 conv-s1,3×3conv-s2,3×3 conv-s1, 80.6 84
3×3 conv-s2,3×3conv-s1,3×3 conv-s1 81.0 85

Table 2. Comparison of different feature fusion methods
View table
Table 2. Comparison of different feature fusion methods
Feature fusion method M_AP /% Speed /(frame·s^-1)
Without fusion 80.4 91
Sum 79.8 96
Concatenation+1×1 conv 81.0 85

Table 3. Comparison of different down-sampling modules
View table
Table 3. Comparison of different down-sampling modules
Down-sampling module M_AP /% Speed /(frame·s^-1)
3×3 conv-s2 79.8 81
2×2 max pool-s2 79.8 84
Mix down-sampling 81.0 85

Table 4. Comparison of different prediction modules
View table
Table 4. Comparison of different prediction modules
Prediction module M_AP /% Speed /(frame·s^-1)
Plain prediction module 80.1 89
Dense prediction module 81.0 85

Table 5. Detection resultsof different backbone networks in SSD, DSOD, and RFBNet models

Table 5. Detection resultsof different backbone networks in SSD, DSOD, and RFBNet models

Backbonenetwork	Depth	Pre-train	SSD		DSOD	RFBNet
Backbonenetwork	Depth	Pre-train	M_AP /%	Speed /(frame·s^-1)			M_AP /%	Speed /(frame·s^-1)	M_AP /%	Speed /(frame·s^-1)
VGG	16	√	77.5		130		78.1	79	78.9	81
VGGBN	16	×	79.5		95		79.5	89	79.9	71
ResNet	101	×	76.0		42		75.5	42	77.1	38
DenseNet	121	×	74.6		37		75.1	32	75.3	29
DS/64-192-48-1	67	×	78.5		51		78.8	47	79.4	42
Root-ResNet-34	34	×	80.2		79		80.6	75	81.3	61
DNet	25	×	80.1		89		81.0	85	80.5	65

Table 6. Detection results of different detectors on the PASCAL VOC dataset

Table 6. Detection results of different detectors on the PASCAL VOC dataset

Method	Pre-train	Backbone network	Input size /(pixel×pixel)	M_AP /%	Speed /(frame·s^-1)
SSD^[11]	√	VGG-16	300×300	77.2	46
SSD^*	√	VGG-16	300×300	77.7	130
YOLOv2^[26]	√	DarkNet-19	544×544	78.6	81
RFBNet^[25]	√	VGG-16	300×300	80.5	83
DSSD^[27]	√	ResNet-101	300×300	78.6	8
Faster R-CNN^[8]	√	ResNet-101	~1000×600	76.4	2.4
RFCN^[28]	√	ResNet-101	~1000×600	80.5	9
DSOD^[19]	×	DS/64-192-48-1	300×300	77.7	17.4
ScratchDet^[20]	×	Root-ResNet-34	300×300	80.4	17.8
Proposed	×	DNet	300×300	81.0	85

Tools

Get Citation

Copy Citation Text

Yalin Song, Yanwei Pang. Backbone Network for Object Detection Task[J]. Laser & Optoelectronics Progress, 2020, 57(4): 041021

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites

Paper Information

Category: Image Processing

Received: Jun. 10, 2019

Accepted: Jul. 22, 2019

Published Online: Feb. 20, 2020

The Author Email: Yalin Song (songyalin@tju.edu.cn)

DOI:10.3788/LOP57.041021

Topics

laser devices and laser physics

Lasers and Laser Optics

laser manufacturing

Instrumentation, Measurement and Metrology