Abstract
With the construction and development of civilized cities, image based garbage classification has gradually become an important concern in computer vision community. During the algorithms for image classification, the strong ability of Convolution Neural Networks (CNNs) in feature learning makes it the most successful approach at the moment. However, the parameters of CNNs model are very huge, and its training usually depends on a large amount of samples. In this article, we tackle the problem of lightweight neural network based garbage image classification, which aims to learn classifier with a small number of model parameters. Specifically, we utilize the MobileNetV2 for the backbone of feature extraction network and jointly train such two nets in a way of deep mutual learning. It realizes the information distillation between the teacher and the student. With this, we can significantly improve the learning ability of the MobileNetV2 based lightweight neural network. The experimental results on a self-assembled dataset show that our proposal effectively classifies the garbage and achieves a classification effect batter than the state of the arts in terms of testing accuracy, time and model size.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Liu, Q.X.: Research on comprehensive treatment of municipal solid waste. Smart City (9), 226–227 (2016)
Ma, Y.J., Fang, K., Wang D.C.: Research on pipeline inner surface image classification method based on support vector machine and distance measurement. Data Acquisition Process. (02):151–155 (2002)
Li, T., Wang J.P., Wu X.Q., Zhang, S.Y.: SVM learning strategy based on improved LBG algorithm. Fudan J. (Natural Science Edition), (05), 789–792 (2004)
Ren, Y.: Research on Image Scene Classification Based on LDA Topic Model[D]. North University of China, (2017)
Lécun, Y., Bottou, L., Bengio, Y.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)
Alex, K., Ilya, S., Geoffrey, E.H..: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097–1105 (2012)
Simonyan, K., Andrew Z.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556(2014)
He, K., Zhang, X.Y., Ren, S.Q., Jian, S.: Deep residual learning for image recognition arXiv preprint arXiv:1512.03385 (2015)
Andrew, G.H., Zhu, M.L., Chen, B., Dmitry, K.: MobileNets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)
Mark, S., Andrew, H., Zhu, M..: MobileNetV2: Inverted Residuals and Linear Bottlenecks. arXiv preprint arXiv:801.04381 (2019)
Zhang, Y., Xiang, T., Timothy, M., Lu, H.C.: Deep Mutual Learning. arXiv preprint arXiv:1706.00384 (2017)
Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. Comput. Sci. 14(7), 38–39 (2015)
Cortes, C., Vapnik, V.: Support-vector networks. Mach. Learn. 20(3), 273–297 (1995)
Rahmi, A.A., Şeref, R.K., Mahmut, K.: Classification of TrashNet dataset based on deep learning models. In: 2018 IEEE International Conference on Big Data, pp. 2058–2062 (2018)
Umut, O., Levent, S.: Fine-tuning models comparisons on garbage classification for recyclability. arXiv:1908.04393 (2019)
Mittal, G, Yagnik, K.B., Garg, M.: SpotGarbage: smartphone app to detect garbage using deep learning. In: 2016 ACM International Joint Conference (2016)
Wu, J., Chen, H., F. Wu.: Research on waste and garbage analysis and identification based on computer vision. Inf. Technol. Informatization 16(10), 81–83 (2016)
Xiang, W., Shi, J.F., Liu, G.H.: Application of improved CaffeNet model in water surface garbage identification. Sens. Microsyst. Syst. 38(8), 150–156 (2019)
Zheng, L.H., Yuan, Z.Q., Yin, C.B.: Research on automatic classification system of construction waste based on machine vision. Mech. Eng. Autom. 2019(6), 16–18 (2019)
Liu, W., Wen, Y., Yu, Z.: Large-margin softmax loss for convolutional neural networks. In: Proceedings of the 33rd International Conference on Machine Learning, pp. 507–516 (2016)
Acknowledgements
This work was supported by the Youth Project of the Provincial Natural Science Foundation of Anhui Province 1908085QF285 and 1908085QF262, the National Natural Science Foundation of China Grant 61672204, the Anhui Provincial Education Department Project, KJ2019A0834 and KJ2019A0835, the Key Research Plan of Anhui 201904d07020002, the Scientific Research and Development Fund of Hefei University 19ZR05ZDA, the Talent Research Fund Project of Hefei University 18-19RC26.
Disclosure
All authors declare that there are no conflicts of interests. All authors declare that they have no significant competing financial, professional or personal interests that might have influenced the performance or presentation of the work described in this manuscript. Declarations of interest: none. All authors approve the final article.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Liu, X., Wu, ZZ., Wu, ZJ., Zou, L., Xu, LX., Wang, XF. (2021). Lightweight Neural Network Based Garbage Image Classification Using a Deep Mutual Learning. In: Ning, L., Chau, V., Lau, F. (eds) Parallel Architectures, Algorithms and Programming. PAAP 2020. Communications in Computer and Information Science, vol 1362. Springer, Singapore. https://doi.org/10.1007/978-981-16-0010-4_19
Download citation
DOI: https://doi.org/10.1007/978-981-16-0010-4_19
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-0009-8
Online ISBN: 978-981-16-0010-4
eBook Packages: Computer ScienceComputer Science (R0)