Light-Weight Multi-Object Detection Network Based on Inverted Residual Structure

Wanjun Liu; Mingyue Gao; Haicheng Qu; Lamei Liu

doi:10.3788/LOP56.221003

Journals >Laser & Optoelectronics Progress >Volume 56 >Issue 22 >Page 221003 > Article

Laser & Optoelectronics Progress
Vol. 56, Issue 22, 221003 (2019)

Light-Weight Multi-Object Detection Network Based on Inverted Residual Structure

Wanjun Liu, Mingyue Gao, Haicheng Qu^*, and Lamei Liu

Author Affiliations

College of Software, Liaoning Technical University, Huludao, Liaoning 125105, China

show less

DOI: 10.3788/LOP56.221003 Cite this Article Set citation alerts

Wanjun Liu, Mingyue Gao, Haicheng Qu, Lamei Liu. Light-Weight Multi-Object Detection Network Based on Inverted Residual Structure[J]. Laser & Optoelectronics Progress, 2019, 56(22): 221003 Copy Citation Text

show less

Fig. 1. Decoupling process of the depth separable convolution. (a) Standard convolution; (b) depth separable convolution

Download full size

Fig. 2. Residual block and inverted residual block. (a) Residual block; (b) inverted residual block when stride is 1

Download full size

Fig. 3. IR-YOLO network architecture

Download full size

Fig. 4. Train loss curves

Download full size

Fig. 5. Class detection accuracy histogram

Download full size

Fig. 6. Comparison of detection results. (a)(d) Original input images ; (b)(e) detection results with YOLOv3-Tiny Model; (c)(f) detection results with IR-YOLO Model

Download full size

Input	Operation	Output
h×w×k	1×1 pointconv, ReLU	h×w×2k
h×w×2k	3×3/sdepth conv, ReLU	$\begin{matrix} \frac{h}{s} \end{matrix}$ × $\begin{matrix} \frac{w}{s} \end{matrix}$ ×2k
$\begin{matrix} \frac{h}{s} \end{matrix}$ × $\begin{matrix} \frac{w}{s} \end{matrix}$ ×2k	1×1 pointconv, linear	$\begin{matrix} \frac{h}{s} \end{matrix}$ × $\begin{matrix} \frac{w}{s} \end{matrix}$ ×2k

Table 1. Parameters of inverted residual block

Category	Train set	Test set
Aeroplane	1171	285
Bicycle	1064	337
Bird	1605	459
Boat	1140	263
Bottle	1764	469
Bus	822	213
Car	3267	1201
Cat	1593	358
Chair	3152	756
Cow	847	244
Dining table	824	206
Dog	2025	489
Horse	1072	348
Motor bike	1052	325
Person	13256	4528
Potted plant	1487	480
Sheep	1070	242
Sofa	814	239
Train	925	282
TV monitor	1108	308
Total	40058	12032

Table 2. VOC dataset

Parameters name	Value
Batch	64
Momentum	0.9
Weight decay	0.0005
Learning rate	0.001

Table 3. Hyper parameters

Input	Output	Number of floatingpoint operations instandard conv /10⁹	Number of floating pointoperations in inverted residual block /10⁹
Input	Output	Number of floatingpoint operations instandard conv /10⁹	Expand point conv	Depth conv	Squeeze point conv
208×208×16	208×208×32	0.399	0.044	0.025	0.089
104×104×32	104×104×64	0.399	0.044	0.012	0.089
52×52×64	52×52×128	0.399	0.044	0.006	0.089
26×26×128	26×26×256	0.399	0.044	0.003	0.089
13×13×256	13×13×512	0.399	0.044	0.002	0.089
13×13×512	13×13×1024	1.595	0.177	0.003	0.354

Table 4. Comparison on number of floating point operations

Model	CPU speed /(frame·s^-1)	GPU speed /(frame·s^-1)
YOLOv3-Tiny	1.2	31.3
IR-YOLO	1.7	31.2

Table 5. Comparison detection speed of IR-YOLO model and YOLOv3-Tiny model

Trainingnumber	YOLOv3-TinymAP /%	IR-YOLOmAP /%
65000	45.15	43.33
75000	45.60	44.37
85000	45.17	45.23
90000	42.75	44.20
95000	42.76	46.07

Table 6. Comparison mAP of different training numbers

Category	YOLOv3-Tiny	IR-YOLO
Aeroplane	54.78	56.38
Bicycle	60.79	57.86
Bird	27.24	28.19
Boat	27.9	28.92
Bottle	14.8	17.58
Bus	56.98	58.48
Car	63.8	64.05
Cat	50.39	53.57
Chair	25.77	23.25
Cow	46.43	45.48
Dining table	39.66	45.48
Dog	46.09	45.68
Horse	66.62	62.45
Motor bike	64.09	62.85
Person	59.23	59.4
Potted plant	18.22	17.22
Sheep	47.57	44.68
Sofa	39.39	43.11
Train	54.02	58.25
TV monitor	50.34	48.62
mAP	45.60	46.07

Table 7. Comparison of detection results of IR-YOLO and YOLOv3-Tiny on VOC dataset%

Wanjun Liu, Mingyue Gao, Haicheng Qu, Lamei Liu. Light-Weight Multi-Object Detection Network Based on Inverted Residual Structure[J]. Laser & Optoelectronics Progress, 2019, 56(22): 221003

Download Citation

Set citation alerts for the article

Tools

Set citation alerts for the article

Save the article for my favorites

Paper Information