Informatics and Applications
2023, Volume 17, Issue 3, pp 88-92
EFFICIENCY OF BINARY NEURAL NETWORKS FOR OBJECT DETECTION ON AN IMAGE
- D. O. Korolev
- O. G. Maleev
Abstract
Deep convolutional neural networks are widely used for object detection. However, modern deep convolutional neural network models are computationally expensive hindering their deployment in resource- constrained mobile and embedded devices. Binary neural networks help to alleviate the resource requirements of devices. Activations and weights in binary neural networks are limited by binary values (-1,1). The proposed method implements balancing and standardization of floating-point weights in forward propagation and two-stage sign function approximation in back propagation. The paper presents the results of detection accuracy on the PASCAL Face dataset as well as the results of speed and model size on the mobile device for the proposed method, the model without binarization, the TinyML network, and Bi-Real Net and ABC-Net methods.
[+] References (15)
- Pathak, A. R., M. Pandey, and S. S. Rautaray. 2018. Application of deep learning for object detection. Proce- dia Comput. Sci. 132:1706-1717. doi: 10.1016/j.procs.2018.05.144.
- Jiao, L., F. Zhang, F Liu, S. Yang, L. Li, Z. Feng, and R. Qu. 2019. A survey of deep learning-based object detection. IEEE Access 7:128837-128868. doi: 10.1109/ ACCESS.2019.2939201.
- Lu, S., B. Wang, H. Wang, L. Chen, M. Linjian, and X. Zhang. 2019. A real-time object detection algorithm forvideo. Comput. Electr. Eng. 77:398-408. doi: 10.1016/ j.compeleceng.2019.05.009.
- Wu, X., D. Sahoo, and S. C. Hoi. 2020. Recent advances in deep learning for object detection. Neurocomputing 396:39-64. doi: 10.1016/j.neucom.2020.01.085.
- Qin, H., R. Gong, X. Liu, M. Shen, Z. Wei, F. Yu, and J. Song. 2020. Forward and backward information retention for accurate binary neural networks. Conference on Computer Vision and Pattern Recognition Pro-ceedings. Seattle, WA: IEEE. 2247-2256. doi: 10.1109/ CVPR42600.2020.00232.
- Qin, H., R. Gong, X. Liu, X. Bai, J. Song, and N. Sebe.
2020. Binary neural networks: A survey. Pattern Recogn. 105:107281. 14 p. doi: 10.1016/j.patcog.2020.107281.
- Liu, W, D. Anguelov, D. Erhan, C. Szegedy, S. E. Reed,
C. Fu, and A. C. Berg. 2016. SSD: Single shot MultiBox detector. Computer vision. Eds. B. Leibe, J. Matas, N. Sebe, and M. Welling. Lecture notes in computer science ser. Cham: Springer. 9905:21-37. doi: 10.1007/978-3-319- 46448-0_2.
- Cai, Z., X. He, J. Sun, and N. Vasconcelos. 2017. Deep learning with low precision by half-wave Gaussian
quantization. Conference on Computer Vision and Pattern Recognition Proceedings. IEEE. 5406-5414. doi: 10.1109/ CVPR.2017.574.
- Ren, S., K. He, R. B. Girshick, and J. Sun. 2017. Faster R-CNN: Towards real-time object detection with region proposal networks. IEEE T. Pattern Anal. 39(6):1137- 1149. doi: 10.1109/TPAMI.2016.2577031.
- Yang, S., P. Luo, C. C. Loy, andX. Tang. 2016. WIDER FACE: A face detection benchmark. Conference on Computer Vision and Pattern Recognition Proceedings. IEEE. 5525-5533. doi: 10.1109/CVPR.2016.596.
- Yan, J., X. Zhang, Z. Lei, and S. Li. 2014. Face detection by structural models. Image Vision Comput. 32(10):790- 799. doi: 10.1016/j.imavis.2013.12.004.
- Zhang, J., Y. Pan, T. Yao, H. Zhao, and T. Mei. 2019. daBNN: A super fast inference framework for binary neural networks on ARM devices. 27th ACM Conference (International) on Multimedia Proceedings. New York, NY ACM. 2272-2275. doi: 10.1145/3343031.3350534.
- Liu, Z., B. Wu, W Luo, X. Yang, W Liu, and K. Cheng.
2018. Bi-Real Net: Enhancing the performance of 1-bit CNNs with improved representational capability and advanced training algorithm. Computer vision. Eds. V. Ferrari, M. Hebert, C. Sminchisescu, and Y Weiss. Lecture notes in computer science ser. Cham: Springer. 11219:747-763. doi: 10.1007/978-3-030-01267-0_44.
- Lin, X., C. Zhao, and W Pan. 2017. Towards accurate binary convolutional neural network. 31st Conference (International) on Neural Information Processing Systems Proceedings. Red Hook, NY: Curran Associates Inc. 345353.
- TensorFlow. TensorFlow Lite guide. Available at: https:// www.tensorflow.org/lite (accessed July 13, 2023).
[+] About this article
Title
EFFICIENCY OF BINARY NEURAL NETWORKS FOR OBJECT DETECTION ON AN IMAGE
Journal
Informatics and Applications
2023, Volume 17, Issue 3, pp 88-92
Cover Date
2023-10-10
DOI
10.14357/19922264230312
Print ISSN
1992-2264
Publisher
Institute of Informatics Problems, Russian Academy of Sciences
Additional Links
Key words
binary neural networks; convolutional neural networks; objects detection; model acceleration
Authors
D. O. Korolev  and O. G. Maleev
Author Affiliations
Peter the Great St. Petersburg Polytechnic University, 29 Polytechnicheskaya Str., St. Petersburg 195251, Russian Federation
|