A Multi-label Scene Categorization Model Based on Deep Convolutional Neural Network
Being one of the most fundamental embranchments of deep learning theory, scene categorization technology has been extensively researched because of its great value in engineering application, especially in the field of remote monitoring and intelligent fault detection. To bridge the gap between theoretical accuracy and practical performance of relevant classification models which is mainly caused by nonstandard labeling information, this paper builds a normative dataset composed of 10,000 high-quality manual labeled images from the power sector, and proposes a high-performance multi-label classification model utilizing deep convolutional neural network (CNN) inspired by Inception-v4  on this basis. Experiments demonstrate that the model proposed achieves an accuracy of 94.125% on the test set and thus can be deployed into practical intelligent surveillance scenarios.
KeywordsMulti-label Scene categorization CNN
This research was supported by the project as follows: Science and Technology Project of SGCC “Research on feature recognition and prediction of typical ice and wind disaster for transmission lines based on small sample machine learning method”.
- 1.Szegedy, C., Ioffe, S., Vanhoucke, V., Alemi, A.A.: Inception-v4, inception-ResNet and the impact of residual connections on learning. In: Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, pp. 4278–4284 (2017)Google Scholar
- 2.Lecun, Y., Bottou, L., Bengio, Y., Ha, P.: Gradient-based learning applied to document recognition. Proc. IEEE, 1–46 (1998)Google Scholar
- 10.Krizhevsky, A., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. Adv. Neural Inf. Process. Syst. 25(2), 1–9 (2012)Google Scholar
- 11.Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., Rabinovich, A.: Going deeper with convolutions. Comput. Vis. Pattern Recognit. 1–9 (2015)Google Scholar
- 12.Lin, A., Chen, Q., Yan, S.: Network in network. Comput. Sci. 1–10 (2013)Google Scholar
- 13.Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. 448–456 (2015)Google Scholar
- 14.Szegedy, C., Vanhoucke, V., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. 2818–2826 (2015)Google Scholar
- 15.He, Z., Zhang, X., Ren, S., Sun, S.: Deep residual learning for image recognition. 770–778 (2015)Google Scholar