Backbone Network for Object Detection Task

Yalin Song; Yanwei Pang

doi:10.3788/LOP57.041021

Journals >Laser & Optoelectronics Progress >Volume 57 >Issue 4 >Page 041021 > Article

Laser & Optoelectronics Progress
Vol. 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

DOI: 10.3788/LOP57.041021 Cite this Article Set citation alerts

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

show less

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

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 1. Comparison of different initial modules

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 2. Comparison of different feature fusion methods

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 3. Comparison of different down-sampling modules

Prediction module	M_AP /%	Speed /(frame·s^-1)
Plain prediction module	80.1	89
Dense prediction module	81.0	85

Table 4. Comparison of different prediction modules

Backbonenetwork	Depth	Pre-train	SSD		DSOD
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 5. Detection resultsof different backbone networks in SSD, DSOD, and RFBNet models

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

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

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

Download Citation

Set citation alerts for the article

Tools

Set citation alerts for the article

Save the article for my favorites

Paper Information