Deep Learning-Based Lightweight Target Detection
DOI:
https://doi.org/10.54097/gxvv0r79Keywords:
shufflenet, mobilenet, senet.Abstract
With the rapid development of computer vision technology, target detection techniques have also been widely used in various fields. However, traditional target detection methods usually require a large amount of computational resources and complex model structures, which pose challenges to the realization and deployment of target detection. Therefore, lightweight target detection methods arise. Lightweight target detection methods refer to reducing the computational and parametric quantities of the model as much as possible while keeping the detection accuracy unchanged. The emergence of this method can not only improve the speed and efficiency of target detection, but also make the target detection technology more adaptable to embedded devices and other resource-limited scenarios. In this paper, through the summary of the deep learning method, the impact on the accuracy and the reduction of computation is compared to give a reference to the subsequent embedded systems or small computational amount of system lightweighting.
Downloads
References
Yang J, Li S, Wang Z, et al. Detecting manufacturing defects using deep learning: A comprehensive survey and current challenges [J]. Materials, 2020, 13(24): 5755.
Yun Jie, Jiang De, Liu Y, et al. Real-time target detection method based on lightweight convolutional neural network [J]. Frontiers of Bioengineering and Biotechnology, 2022, 10: 861286.
Zhang Xiao, Zhou Xiao, Lin Ming, et al. Shufflenet: An extremely efficient convolutional neural network for mobile devices [C] // Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018: 6848-6856.
Howard, A. G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., ... & Adam, H. Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861. 2017
Hu J, Shen L, Sun G. Squeeze excitation network [C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018:7132-7141.
Molchanov P, Mallya A, Tyree S, et al. Importance estimation of neural network pruning [C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2019:11264-11272.
Huang Z, Wang N. Data-driven sparse structure selection for deep neural networks [C]//Proceedings of the European Conference on Computer Vision (ECCV). 2018: 304-320.
Han S, Mao H, Dally W J. Deep compression: compressing deep neural networks using pruning, training quantization, and Huffman coding[J]. arXiv preprint arXiv:1510.00149, 2015.
Molchanov, P., Tyree, S., Karras, T., Aila, T., & Kautz, J. Pruning convolutional neural networks for resource efficient inference. arXiv preprint arXiv:1611.06440. 2016
Li, H., Kadav, A., Durdanovic, I., Samet, H., & Graf, H. P. Pruning filters for efficient convnets. arXiv preprint arXiv:1608.08710. 2016
He Y, Zhang Xu, Sun Jie. Accelerating channel pruning of extremely deep neural networks [C]//Proceedings of the IEEE International Conference on Computer Vision. 2017: 1389-1397.
Downloads
Published
Issue
Section
License
Copyright (c) 2024 Highlights in Science, Engineering and Technology
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
How to Cite
