A Design of Model Compression Method Based on YOLOv5
DOI:
https://doi.org/10.54097/2hzc5r49Keywords:
Object Detection, Model Compression, Pruning, Logical Distillation.Abstract
In response to the requirements for detection accuracy and speed in security detection technology in current smart city construction, a model compression method based on YOLOv5s is proposed, aiming to lighten the original model and detect the opening and closing states of car windows. Firstly, a structured pruning method based on channel weights is employed to perform channel pruning. Then, a fine-tuning training method based on logical distillation is adopted to restore the network detection accuracy. Experimental results on the car window dataset show that compared with the original algorithm, the improved algorithm only loses 0.3% in detection accuracy while reducing the number of parameters and computations to 41.5% and 44.3% of the original model, respectively. This significantly reduces the model complexity and achieves model lightweighting.
Downloads
References
Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014). Rich feature hierarchies for accurate object detection and semantic segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 580-587).
Girshick, R. (2015). Fast r-cnn. In Proceedings of the IEEE international conference on computer vision (pp. 1440-1448).
Ren, S., He, K., Girshick, R., & Sun, J. (2015). Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems, 28.
Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016). You only look once: Unified, real-time object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 779-788).
Redmon, J., & Farhadi, A. (2017). YOLO9000: better, faster, stronger. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 7263-7271).
Redmon, J., & Farhadi, A. (2018). Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767.
Bochkovskiy, A., Wang, C. Y., & Liao, H. Y. M. (2020). Yolov4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934.
Hinton, G., Vinyals, O., & Dean, J. (2015). Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531.
Luo, J. H., Wu, J., & Lin, W. (2017). Thinet: A filter level pruning method for deep neural network compression. In Proceedings of the IEEE international conference on computer vision (pp. 5058-5066).
He, Y., Zhang, X., & Sun, J. (2017). Channel pruning for accelerating very deep neural networks. In Proceedings of the IEEE international conference on computer vision (pp. 1389-1397).
Hubara, I., Courbariaux, M., Soudry, D., El-Yaniv, R., & Bengio, Y. (2018). Quantized neural networks: Training neural networks with low precision weights and activations. Journal of Machine Learning Research, 18(187), 1-30.
Jacob, B., Kligys, S., Chen, B., Zhu, M., Tang, M., Howard, A., ... & Kalenichenko, D. (2018). Quantization and training of neural networks for efficient integer-arithmetic-only inference. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 2704-2713).
Zhang, X., Zou, J., He, K., & Sun, J. (2015). Accelerating very deep convolutional networks for classification and detection. IEEE transactions on pattern analysis and machine intelligence, 38(10), 1943-1955.
Lebedev, V., Ganin, Y., Rakhuba, M., Oseledets, I., & Lempitsky, V. (2014). Speeding-up convolutional neural networks using fine-tuned cp-decomposition. arXiv preprint arXiv:1412.6553.
Downloads
Published
Issue
Section
License
Copyright (c) 2024 Academic Journal of Science and Technology
This work is licensed under a Creative Commons Attribution 4.0 International License.
