1. bookVolume 23 (2018): Issue 2 (December 2018)
Journal Details
License
Format
Journal
First Published
08 Nov 2012
Publication timeframe
2 times per year
Languages
English
access type Open Access

An Efficient Technique for Size Reduction of Convolutional Neural Networks after Transfer Learning for Scene Recognition Tasks

Published Online: 31 Dec 2018
Page range: 141 - 149
Journal Details
License
Format
Journal
First Published
08 Nov 2012
Publication timeframe
2 times per year
Languages
English

A complex classification task as scene recognition is considered in the present research. Scene recognition tasks are successfully solved by the paradigm of transfer learning from pretrained convolutional neural networks, but a problem is that the eventual size of the network is huge despite a common scene recognition task has up to a few tens of scene categories. Thus, the goal is to ascertain possibility of a size reduction. The modelling recognition task is a small dataset of 4485 grayscale images broken into 15 image categories. The pretrained network is AlexNet dealing with much simpler image categories whose number is 1000, though. This network has two fully connected layers, which can be potentially reduced or deleted. A regular transfer learning network occupies about 202.6 MB performing at up to 92 % accuracy rate for the scene recognition. It is revealed that deleting the layers is not reasonable. The network size is reduced by setting a fewer number of filters in the 17th and 20th layers of the AlexNet-based networks using a dichotomy principle or similar. The best truncated network with 384 and 192 filters in those layers performs at 93.3 % accuracy rate, and its size is 21.63 MB.

Keywords

[1] S. M. Salaken, A. Khosravi, T. Nguyen, and S. Nahavandi, “Extreme learning machine based transfer learning algorithms: A survey,” Neurocomputing, vol. 267, pp. 516–524, 2017. https://doi.org/10.1016/j.neucom.2017.06.037Search in Google Scholar

[2] D. Han, Q. Liu, and W. Fan, “A new image classification method using CNN transfer learning and web data augmentation,” Expert Systems with Applications, vol. 95, pp. 43–56, 2018. https://doi.org/10.1016/j.eswa.2017.11.028Search in Google Scholar

[3] L. Wang, L. Ge, R. Li, and Y. Fang, “Three-stream CNNs for action recognition,” Pattern Recognition Letters, vol. 92, pp. 33–40, 2017. https://doi.org/10.1016/j.patrec.2017.04.004Search in Google Scholar

[4] V. Campos, B. Jou, and X. Giró-i-Nieto, “From pixels to sentiment: Fine-tuning CNNs for visual sentiment prediction,” Image and Vision Computing, vol. 65, pp. 15–22, 2017. https://doi.org/10.1016/j.imavis.2017.01.011Search in Google Scholar

[5] L. H. S. Vogado, R. M. S. Veras, F. H. D. Araujo, R. R. V. Silva, and K. R. T. Aires, “Leukemia diagnosis in blood slides using transfer learning in CNNs and SVM for classification,” Engineering Applications of Artificial Intelligence, vol. 72, pp. 415–422, 2018. https://doi.org/10.1016/j.engappai.2018.04.024Search in Google Scholar

[6] A. Khatami, M. Babaie, H. R. Tizhoosh, A. Khosravi, T. Nguyen, and S. Nahavandi, “A sequential search-space shrinking using CNN transfer learning and a Radon projection pool for medical image retrieval,” Expert Systems with Applications, vol. 100, pp. 224–233, 2018. https://doi.org/10.1016/j.eswa.2018.01.056Search in Google Scholar

[7] X. Cheng, J. Lu, J. Feng, B. Yuan, and J. Zhou, “Scene recognition with objectness,” Pattern Recognition, vol. 74, pp. 474–487, 2018. https://doi.org/10.1016/j.patcog.2017.09.025Search in Google Scholar

[8] X. Song, S. Jiang, L. Herranz, Y. Kong, and K. Zheng, “Category co-occurrence modeling for large scale scene recognition,” Pattern Recognition, vol. 59, pp. 98–111, 2016. https://doi.org/10.1016/j.patcog.2016.01.019Search in Google Scholar

[9] S. Gould, R. Fulton, and D. Koller, “Decomposing a scene into geometric and semantically consistent regions,” Proceedings of 2009 IEEE 12th International Conference on Computer Vision, pp. 1–8, 2009. https://doi.org/10.1109/iccv.2009.5459211Search in Google Scholar

[10] Z. Ding, M. Shao, and Y. Fu, “Incomplete multisource transfer learning,” IEEE Transactions on Neural Networks and Learning Systems, vol. 29, no. 2, pp. 310–323, 2018. https://doi.org/10.1109/TNNLS.2016.2618765Search in Google Scholar

[11] H. Zhao, Q. Liu, and Y. Yang, “Transfer learning with ensemble of multiple feature representations,” Proceedings of 2018 IEEE 16th International Conference on Software Engineering Research, Management and Applications (SERA), pp. 54–61, 2018. http://doi.ieeecomputersociety.org/10.1109/SERA.2018.8477189Search in Google Scholar

[12] H. Azizpour, A. S. Razavian, J. Sullivan, A. Maki, and S. Carlsson, “Factors of transferability for a generic ConvNet representation,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 38, no. 9, pp. 1790–1802, 2016. https://doi.org/10.1109/TPAMI.2015.2500224Search in Google Scholar

[13] S. Bai, and H. Tang, “Softly combining an ensemble of classifiers learned from a single convolutional neural network for scene categorization,” Applied Soft Computing, vol. 67, pp. 183–196, 2018. https://doi.org/10.1016/j.asoc.2018.03.007Search in Google Scholar

[14] P. Tang, H. Wang, and S. Kwong, “G-MS2F: GoogLeNet based multi-stage feature fusion of deep CNN for scene recognition,” Neurocomputing, vol. 225, pp. 188–197, 2017. https://doi.org/10.1016/j.neucom.2016.11.023Search in Google Scholar

[15] A. Krizhevsky, I. Sutskever, and G. E. Hinton, “ImageNet classification with deep convolutional neural networks,” Communications of the ACM, vol. 60, no. 2, pp. 84–90, 2017. https://doi.org/10.1145/3065386Search in Google Scholar

[16] C. Wang, J. Yu, and D. Tao, “High-level attributes modeling for indoor scenes classification,” Neurocomputing, vol. 121, pp. 337–343, 2013. https://doi.org/10.1016/j.neucom.2013.05.032Search in Google Scholar

[17] S. Bai, “Growing random forest on deep convolutional neural networks for scene categorization,” Expert Systems with Applications, vol. 71, pp. 279–287, 2017. https://doi.org/10.1016/j.eswa.2016.10.038Search in Google Scholar

[18] B.-J. Han, and J.-Y. Sim, “Saliency detection for panoramic landscape images of outdoor scenes,” Journal of Visual Communication and Image Representation, vol. 49, pp. 27–37, 2017. https://doi.org/10.1016/j.jvcir.2017.08.003Search in Google Scholar

[19] J.-T. Lee, H.-U. Kim, C. Lee, and C.-S. Kim, “Photographic composition classification and dominant geometric element detection for outdoor scenes,” Journal of Visual Communication and Image Representation, vol. 55, pp. 91–105, 2018. https://doi.org/10.1016/j.jvcir.2018.05.018Search in Google Scholar

[20] B. Liu, S. Gould, and D. Koller, “Single image depth estimation from predicted semantic labels,” Proceedings of 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 1253–1260, 2010. https://doi.org/10.1109/cvpr.2010.5539823Search in Google Scholar

[21] V. V. Romanuke, “Appropriate number and allocation of ReLUs in convolutional neural networks,” Research Bulletin of the National Technical University of Ukraine “Kyiv Polytechnic Institute”, no. 1, pp. 69–78, 2017. https://doi.org/10.20535/1810-0546.2017.1.88156Search in Google Scholar

[22] V. Romanuke, “Optimal training parameters and hidden layer neuron number of two-layer perceptron for generalised scaled object classification problem,” Information Technology and Management Science, vol. 18, no. 1, pp. 42–48, 2015. https://doi.org/10.1515/itms-2015-0007Search in Google Scholar

[23] V. V. Romanuke, “Interval uncertainty reduction via division-by-2 dichotomization based on expert estimations for short-termed observations,” Journal of Uncertain Systems, vol. 1, no. 12, pp. 3–21, 2018.Search in Google Scholar

[24] J. Yang, S. Li, and W. Xu, “An iterative transfer learning based classification framework,” Proceedings of 2018 International Joint Conference on Neural Networks (IJCNN), pp. 1–8, 2018. https://doi.org/10.1109/IJCNN.2018.8489471Search in Google Scholar

[25] X. Liu, Z. Liu, G. Wang, Z. Cai, and H. Zhang, “Ensemble transfer learning algorithm,” IEEE Access, vol. 6, pp. 2389–2396, 2018. https://doi.org/10.1109/ACCESS.2017.2782884Search in Google Scholar

[26] Y. Liu, D. Yang, and C. Zhang, “Relaxed conditions for convergence analysis of online back-propagation algorithm with regularizer for Sigma-Pi-Sigma neural network,” Neurocomputing, vol. 272, pp. 163–169, 2018. https://doi.org/10.1016/j.neucom.2017.06.057Search in Google Scholar

Recommended articles from Trend MD

Plan your remote conference with Sciendo