Vehicle Appearance Recognition Using Shared Lightweight Convolutional Neural Networks

Qing Kang; Hongdong Zhao; Dongxu Yang

doi:10.3788/LOP202158.0210013

Journals >Laser & Optoelectronics Progress >Volume 58 >Issue 2 >Page 0210013 > Article

Laser & Optoelectronics Progress
Vol. 58, Issue 2, 0210013 (2021)

Vehicle Appearance Recognition Using Shared Lightweight Convolutional Neural Networks

Qing Kang, Hongdong Zhao^*, and Dongxu Yang

Author Affiliations

School of Electronics and Information Engineering, Hebei University of Technology,Tianjin 300401, China

show less

DOI: 10.3788/LOP202158.0210013 Cite this Article Set citation alerts

Qing Kang, Hongdong Zhao, Dongxu Yang. Vehicle Appearance Recognition Using Shared Lightweight Convolutional Neural Networks[J]. Laser & Optoelectronics Progress, 2021, 58(2): 0210013 Copy Citation Text

show less

Fig. 1. Fire module structure

Download full size

Fig. 2. Structure comparison. (a) FC; (b) GAP

Download full size

Fig. 3. Structure of networks. (a) No-shared; (b) partly-shared; (c) fully-shared

Download full size

Fig. 4. Example of vehicle images in Opendata_VRID dataset

Download full size

Fig. 5. Dataset distribution. (a) Vehicle type; (b) vehicle color

Download full size

Fig. 6. Result comparison between different “slimming” SqueezeNet. (a) Training loss of color recognition; (b) validation accuracy of color recognition; (c) training loss of vehicle type recognition; (d) validation accuracy of vehicle type recognition

Download full size

Fig. 7. Result comparison for vehicle type recognition. (a) Training loss; (b) validation accuracy

Download full size

Fig. 8. Result comparison for vehicle color recognition. (a) Training loss; (b) validation accuracy

Download full size

Number	Layer	Filter shape (N: number of categories)
Number	Layer	SqueezeNet	Squeeze1	Squeeze2	Squeeze3
0	Conv1	96 × 3 × 7 ×7	48 × 3 × 7 ×7	24 × 3 × 7 ×7	12 × 3 × 7 ×7
1	Fire2/Squeeze1×1	16 × 96 × 1 × 1	8 × 48 × 1 × 1	4 × 24 × 1 × 1	2 × 12 × 1 × 1
2	Fire2/Expand3×3	64 × 16 × 3 × 3	32 × 8 × 3 × 3	16 × 4 × 3 × 3	8 × 2 × 3 × 3
3	Fire3/Squeeze1×1	16 × 128 × 1 × 1	8 × 64 × 1 × 1	4 × 32 × 1 × 1	2 × 16 × 1 × 1
4	Fire3/Expand3×3	64 × 16 × 3 × 3	32 × 8 × 3 × 3	16 × 4 × 3 × 3	8 × 2 × 3 × 3
5	Fire4/Squeeze1×1	32 × 128 × 1 × 1	16 × 64 × 1 × 1	8 × 32 × 1 × 1	4 × 16 × 1 × 1
6	Fire4/Expand3×3	128 × 32 × 3 × 3	64 × 16 × 3 × 3	32 × 8 × 3 × 3	16 × 4 × 3 × 3
7	Fire5/Squeeze1×1	32 × 256 × 1 × 1	16 × 128 × 1 × 1	8 × 64 × 1 × 1	4 × 32 × 1 × 1
8	Fire5/Expand3×3	128 × 32 × 3 × 3	64 × 16 × 3 × 3	32 × 8 × 3 × 3	16 × 4 × 3 × 3
9	Fire6/Squeeze1×1	48 × 256 × 1 × 1	24 × 128 × 1 × 1	12 × 64 × 1 × 1	6 × 32 × 1 × 1
10	Fire6/Expand3×3	192 × 48 × 3 × 3	96 × 24 × 3 × 3	48 × 12 × 3 × 3	24 × 6 × 3 × 3
11	Fire7/Squeeze1×1	48 × 384 × 1 × 1	24 × 192 × 1 × 1	12 × 96 × 1 × 1	6 × 48 × 1 × 1
Number	Layer	Filter shape (N: number of categories)
Number	Layer	SqueezeNet	Squeeze1	Squeeze2	Squeeze3
12	Fire7/Expand3×3	192 × 48 × 3 × 3	96 × 24 × 3 × 3	48 × 12 × 3 × 3	24 × 6 × 3 × 3
13	Fire8/Squeeze1×1	64 × 384 × 1 × 1	32 × 192 × 1 × 1	16 × 96 × 1 × 1	8 × 48 × 1 × 1
14	Fire8/Expand3×3	256 × 64 × 3 × 3	128 × 32 × 3 × 3	64 × 16 × 3 × 3	32 × 8 × 3 × 3
15	Fire9/Squeeze1×1	64 × 512 × 1 × 1	32 × 256 × 1 × 1	16 × 128 × 1 × 1	8 × 64 × 1 × 1
16	Fire9/Expand3×3	256 × 64 × 3 × 3	128 × 32 × 3 × 3	64 × 16 × 3 × 3	32 × 8 × 3 × 3
17	Conv10	N × 512 × 1 × 1	N × 256 × 1 × 1	N × 128 × 1 × 1	N × 64 × 1 × 1
18	Global average pooling+SoftMax

Table 1. Three “slimming” SqueezeNet structures

Network(basic network+sharing method)	Number of trainable parameters	Number of non-trainable parameters	Number of total parameters
Squeeze1+no-shared	338825	838	339663
Squeeze1+partly-shared	313993	678	314671
Squeeze1+fully-shared	171873	438	172311
Squeeze2+no-shared	90401	438	90839
Squeeze2+partly-shared	82305	358	82663
Squeeze2+fully-shared	46445	238	46683
Squeeze3+no-shared	25469	238	25707
Squeeze3+partly-shared	22501	198	22699
Squeeze3+fully-shared	13371	138	13509

Table 2. Comparison of number of parameters in nine network structures

Network(basic network+sharing method)	Testing accuracy/%		Time cost/ms
Network(basic network+sharing method)	Color	Type	Time cost/ms
Squeeze1+no-shared	98.6	99.2	6.89
Squeeze1+partly-shared	98.5	99.2	4.99
Squeeze1+fully-shared	98.5	99.1	4.42
Squeeze2+no-shared	98.6	99.2	4.11
Squeeze2+partly-shared	98.5	99.0	2.79
Squeeze2+fully-shared	98.4	98.8	2.48
Squeeze3+no-shared	98.3	99.0	3.06
Squeeze3+partly-shared	98.0	98.3	2.01
Squeeze3+fully-shared	97.5	97.0	1.68

Table 3. Result comparison between different networks

Qing Kang, Hongdong Zhao, Dongxu Yang. Vehicle Appearance Recognition Using Shared Lightweight Convolutional Neural Networks[J]. Laser & Optoelectronics Progress, 2021, 58(2): 0210013

Download Citation

Set citation alerts for the article

Tools

Set citation alerts for the article

Save the article for my favorites

Paper Information