A Review of the Lightweight Technology of Object Detection Algorithms

Zexi Tan

doi:10.62051/ijcsit.v4n3.36

Authors

Zexi Tan

DOI:

https://doi.org/10.62051/ijcsit.v4n3.36

Keywords:

Deep Learning, Object detection algorithms, Lightweight technology

Abstract

Deep learning has made significant progress in the field of object detection, especially convolutional neural networks have performed well in image classification, object detection, and segmentation tasks. However, with the increasing complexity of models and the demand for computing resources, traditional deep learning models face challenges in the deployment of resource-constrained mobile and embedded devices. In order to solve this problem, model compression and acceleration techniques have become a research hotspot, including pruning, quantification and knowledge distillation. The purpose of this paper is to review various algorithms in the field of object detection and their advantages and disadvantages, and to discuss the best optimization scheme based on the application and optimization effect of lightweight technology in various algorithms. The research objectives include: systematically summarizing and analyzing the main lightweight technologies currently used for object detection algorithms, evaluating their practical effects in object detection tasks, proposing improvement schemes suitable for specific application scenarios, and looking forward to the future development direction, and discussing potential research directions and technological breakthroughs.

Downloads

Download data is not yet available.

References

[1] Li Kequan, Chen Yan, Liu Jiachen, Mou Xiangwei. Survey of Object Detection Algorithms Based on Deep Learning [J]. Computer Engineering, 2022, 48(7): 1-12.

[2] Ning Xin, Zhao Wenyao, Zong Yixin, Zhang Yugui, Chen Hao, Zhou Qi, Ma Junxiao. A Review of Joint Optimization Methods for Neural Network Compression [J]. Chinese Journal of Intelligent Systems, 2024, 19(1): 36-57.

[3] GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of the IEEE Con ference on Computer Vision and Pattern Recognition, 2014: 580-587.

[4] REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: unified, real-time object detection[C]//Proceed ings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016:779-788.

[5] HE K, GKIOXARI G, DOLLAR P, et al. Mask R-CNN[C]// Proceedings of the IEEE International Conference on Computer Vision, 2017:2980-2988.

[6] HE K M, ZHANG X Y, REN S Q, et al. Spatial pyramid pooling in deep convolutional networks for visual rec ognition [J]. European Conference on Computer Vision, 2014: 346-361.

[7] GIRSHICK R. Fast R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision, 2015:1440-1448.

[8] REN S Q, HE K M, GIRSHICK R, et al.Faster R-CNN: towards real-time object detection with region proposal networks[C]//Advances in Neural Information Processing Systems, 2015:91-99.

[9] LIU W, ANGUELOV D, ERHAN D, et al. SSD:single shot multibox detector[C]//European Conference on Computer Vision, 2016:21-37.

[10] FU C Y, LIU W, RANGA A, et al.DSSD:deconvolutional single shot detector [J]. arXiv:1701.06659, 2017.

[11] LI Z, ZHOU F.FSSD:feature fusion single shot multibox detector [J]. arXiv:1712.00960, 2017.

[12] Aghli, N., & Ribeiro, E. (2021). Combining Weight Pruning and Knowledge Distillation for CNN Compression. CVPRW 2021.

[13] Jani, M., Fayyad, J., Al-Younes, Y., & Najjaran, H. (2023). An SSD-MobileNet Acceleration Strategy for FPGAs Based on Network Compression and Subgraph Fusion. *Forests*. Retrieved from [MDPI] (https://www.mdpi.com/).