Abstract
Convolutional neural networks are global trainable multi-stage architectures that automatically learn translation invariant features from raw input images. However, in tradition they only allow adjacent layers connected, limiting integration of multi-scale information. To further improve their performance in classification, we present a new architecture called shortcut convolutional neural networks. This architecture can concatenate multi-scale feature maps by shortcut connections to form the fully-connected layer that is directly fed to the output layer. We give an investigation of the proposed shortcut convolutional neural networks on gender classification and texture classification. Experimental results show that shortcut convolutional neural networks have better performances than those without shortcut connections, and it is more robust to different settings of pooling schemes, activation functions, initializations, and optimizations.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Comp. Visi. 60(2), 91–110 (2004)
Donoho, D.L., Huo, X.: Beamlets and multiscale image analysis. In: Barth, T.J., Chan, T., Haimes, R. (eds.) Multiscale and Multiresolution Methods, vol. 20, pp. 149–196. Springer, Heidelberg (2001)
Sermanet P., Y. Lecun Y.: Traffic sign recognition wit multi-scale convolutional networks. In: IEEE International Joint Conference on Neural Networks, pp. 2809–2813 (2011)
Glorot, X., Bengio, Y.: Understanding the difficulity of training deep feedforward neural networks. J. Mach. Learn. Res. 9, 249–256 (2010)
He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: surpassing human-level performance on ImageNet classification. In: IEEE Internatioal Conference on Computer Vision, pp. 1026–1034 (2015)
Kingma, D.F., Ba, J.L.: Adam: a method for stochastic optimization. In: 3rd IEEE International Conference on Learning Representation (2015)
Acknowledgments
This work was supported in part by the National Natural Science Foundation of China under grant 61175004,China Postdoctoral Science Foundation funded project(2015M580952), and Beijing Postdoctoral Research Foundation (2016ZZ-24).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Zhang, T., Li, Y., Liu, Z. (2017). Shortcut Convolutional Neural Networks for Classification of Gender and Texture. In: Lintas, A., Rovetta, S., Verschure, P., Villa, A. (eds) Artificial Neural Networks and Machine Learning – ICANN 2017. ICANN 2017. Lecture Notes in Computer Science(), vol 10614. Springer, Cham. https://doi.org/10.1007/978-3-319-68612-7_4
Download citation
DOI: https://doi.org/10.1007/978-3-319-68612-7_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-68611-0
Online ISBN: 978-3-319-68612-7
eBook Packages: Computer ScienceComputer Science (R0)