Abstract
An improved Image classification algorithm based on Darknet53 model is proposed in this paper to solve the problem that a large amount of the same gradient information is repeatedly used to update the weights of different dense layers in the Darknet53 network in the process of back propagation. Firstly, the residual block in the original network is replaced by THE CSP module, referring to the idea of cutting off the gradient flow in CSPnet to prevent too much repeated gradient information. Second, the Mish activation function is used to replace the Leaky ReLU function, which can transmit information more smoothly and achieve better accuracy and generalization. Finally, a SPP module is added to the end of the original network structure to solve the multi-scale problem of the main part of image classification. The experimental results show that the improved Darknet has achieved better performance, and the accuracy is improved by 1.3% compared with the original network; At the same time, compared with resnet50 and resnet101, the improved Darknet has better effect on image classification.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Ouyang, W., Zeng, X., Wang, X., et al.: DeepID-Net: object detection with deformable part based convolutional neural networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(7), 1320–1334 (2017)
Hu, G., Yang, Y.X., Yi, D., et al.: When face recognition meets with deep learning: an evaluation of convolutional neural networks for face recognition. In: International Conference on Computer Vision, Santiago, Chile, 11–18 December 2015, pp. 142–150. IEEE Press, Piscataway (2015)
Cheng, B., **ao, B., Wang, J., Shi, H., Huang, T.S., Zhang, L.: HigherHRNet: scale-aware representation learning for bottom-up human pose estimation. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5385–5394 (2020). https://doi.org/10.1109/CVPR42600.2020.00543
Lecun, Y., Bottou, L., Bengio, Y., et al.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)
Krizhevsky, A., Sutskever, I.E., Hinton, G.: ImageNet classification with deep convolutional neural networks. In: International Conference on Neural Information Processing Systems, Lake Tahoe, Nevada, 3–6 December 2012, pp. 1097–1105. Curran Associates Inc., Red Hook (2012)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: International Conference of Learning Representation, San Diego, CA, 7–9 May 2015 (2015). ar**v:1409.1556v6 [cs.CV]
He, K.M., Zhang, X.Y., Ren, S.Q., et al.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, Nevada, 27–30 June 2016. IEEE Computer Society, Los Alamitos (2016)
Gedy, C., Liu, W., Jia, Y.Q., et al.: Going deeper with convolutions. In: IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA, 7–12 July 2015, pp. 1–9. IEEE Press, Piscataway (2015)
Huang, G., Liu, Z., Maaten, L.V.D., et al.: Densely connected convolutional networks. In: IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, 21–26 July 2017, pp. 2261–2269. IEEE Press, Piscataway (2017)
Redmon, J., Farhadi, A.: Yolov3: an incremental improvement.ar**v Preprint ar**v: 1804.02767 (2018)
Misra, D.: Mish: a self regularized non-monotonic neural activation function (2019)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Zou, S., Zhang, B., Zhang, B. (2023). Research on Improved Image Classification Algorithm Based on Darknet53 Model. In: Liang, Q., Wang, W., Liu, X., Na, Z., Zhang, B. (eds) Communications, Signal Processing, and Systems. CSPS 2022. Lecture Notes in Electrical Engineering, vol 874. Springer, Singapore. https://doi.org/10.1007/978-981-99-2362-5_10
Download citation
DOI: https://doi.org/10.1007/978-981-99-2362-5_10
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-2361-8
Online ISBN: 978-981-99-2362-5
eBook Packages: EngineeringEngineering (R0)