Abstract
Dropout has been widely used to improve the generalization ability of a deep network, while current dropout variants rarely adapt the dropout probabilities of the network hidden units or weights dynamically to their contributions on the network optimization. In this work, a clustering-based dropout based on the network characteristics of features, weights or their derivatives is proposed, where the dropout probabilities for these characteristics are updated self-adaptively according to the corresponding clustering group to differentiate their contributions. Experimental results on the databases of Fashion-MNIST and CIFAR10 and expression databases of FER2013 and CK+ show that the proposed clustering-based dropout achieves better accuracy than the original dropout and various dropout variants, and the most competitive performances compared with state-of-the-art algorithms.
The work was supported by Natural Science Foundation of China under grants no. 61602315, 61672357 and U1713214, the Science and Technology Project of Guangdong Province under grant no. 2018A050501014, the Tencent “Rhinoceros Birds”-Scientific Research Foundation for Young Teachers of Shenzhen University, the School Startup Fund of Shenzhen University under grants no. 2018063.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Liu, S., Deng, W.: Very deep convolutional neural network based image classification using small training sample size. In: 2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR), pp. 730–734 (2015)
Xie, W., Jia, X., Shen, L., Yang, M.: Sparse deep feature learning for facial expression recognition. Pattern Recogn. (PR) 96, 106966 (2019)
Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. (JMLR) 15, 1929–1958 (2014)
Wang, H., Wang, L.: Learning robust representations using recurrent neural networks for skeleton based action classification and detection. In: International Conference on Multimedia Expo Workshops (ICMEW), pp. 591–596, July 2017
Wan, L., Zeiler, M., Zhang, S., Cun, Y.L., Fergus, R.: Regularization of neural networks using DropConnect. In: Proceedings of International Conference on Machine Learning (ICML), vol. 28, pp. 1058–1066, June 2013
Khan, S., Hayat, M., Porikli, F.: Regularization of deep neural networks with spectral dropout. Neural Netw. 110, 82–90 (2019)
Tompson, J., Goroshin, R., Jain, A., LeCun, Y., Bregler, C.: Efficient object localization using convolutional networks. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 648–656 (2014)
Poernomo, A., Kang, D.K.: Biased dropout and crossmap dropout: learning towards effective dropout regularization in convolutional neural network. Neural Netw. 104, 60–67 (2018)
Han, S., Pool, J., Tran, J., Dally, W.: Learning both weights and connections for efficient neural network. In: Advances in Neural Information Processing Systems (NIPS), pp. 1135–1143 (2015)
Rohit, K., Richa, S., Mayank, V.: Guided dropout. In: AAAI Conference on Artificial Intelligence (AAAI) (2019)
Zhang, X., Yang, Y., Feng, J.: ML-LocNet: improving object localization with multi-view learning network. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11207, pp. 248–263. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01219-9_15
Zhang, C., Zhu, C., Xiao, J., Xu, X., Liu, Y.: Image ordinal classification and understanding: grid dropout with masking label. In: 2018 IEEE International Conference on Multimedia and Expo (ICME), pp. 1–6, July 2018
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770–778 (2016)
Wager, S., Wang, S., Liang, P.S.: Dropout training as adaptive regularization. In: Advances in Neural Information Processing Systems (NIPS), pp. 351–359 (2013)
Ba, J., Frey, B.: Adaptive dropout for training deep neural networks. In: Advances in Neural Information Processing Systems (NIPS), pp. 3084–3092 (2013)
Xiao, H., Rasul, K., Vollgraf, R.: Fashion-MNIST: a novel image dataset for benchmarking machine learning algorithms. arXiv preprint arXiv:1708.07747 (2017)
Krizhevsky, A., Hinton, G.: Learning multiple layers of features from tiny images. Master’s thesis, Department of Computer Science, University of Toronto (2009)
Goodfellow, I.J., et al.: Challenges in representation learning: a report on three machine learning contests. In: Lee, M., Hirose, A., Hou, Z.-G., Kil, R.M. (eds.) ICONIP 2013. LNCS, vol. 8228, pp. 117–124. Springer, Heidelberg (2013). https://doi.org/10.1007/978-3-642-42051-1_16
Kanade, T., Cohn, J.F., Tian, Y.: Comprehensive database for facial expression analysis. In: Proceedings Fourth IEEE International Conference on Automatic Face and Gesture Recognition (FG), pp. 46–53 (2000)
De Winter, J.C.: Using the student’s t-test with extremely small sample sizes. Pract. Assess. Res. Eval. 18(10), 1–12 (2013)
Han, S., Mao, H., Dally, W.J.: Deep compression: compressing deep neural networks with pruning, trained quantization and Huffman coding. arXiv preprint arXiv:1510.00149 (2015)
Mollahosseini, A., Chan, D., Mahoor, M.H.: Going deeper in facial expression recognition using deep neural networks. In: 2016 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 1–10 (2016)
Jung, H., Lee, S., Yim, J., Park, S., Kim, J.: Joint fine-tuning in deep neural networks for facial expression recognition. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 2983–2991 (2015)
Tang, Y.: Deep learning using support vector machines. In: Proceedings of International Conference on Machine Learning (ICML) (2013)
Liu, X., Vijaya Kumar, B., You, J., Jia, P.: Adaptive deep metric learning for identity-aware facial expression recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 20–29 (2017)
Courbariaux, M., Bengio, Y., David, J.P.: BinaryConnect: training deep neural networks with binary weights during propagations. In: Advances in Neural Information Processing Systems (NIPS), pp. 3123–3131 (2015)
Wen, G., Hou, Z., Li, H., Li, D., Jiang, L., Xun, E.: Ensemble of deep neural networks with probability-based fusion for facial expression recognition. Cogn. Comput. 9(5), 597–610 (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Wen, Z., Ke, Z., Xie, W., Shen, L. (2020). Clustering-Based Adaptive Dropout for CNN-Based Classification. In: Palaiahnakote, S., Sanniti di Baja, G., Wang, L., Yan, W. (eds) Pattern Recognition. ACPR 2019. Lecture Notes in Computer Science(), vol 12046. Springer, Cham. https://doi.org/10.1007/978-3-030-41404-7_4
Download citation
DOI: https://doi.org/10.1007/978-3-030-41404-7_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-41403-0
Online ISBN: 978-3-030-41404-7
eBook Packages: Computer ScienceComputer Science (R0)