Abstract
The introduction of skip connections used for summing feature maps in deep residual networks (ResNets) were crucially important for overcoming gradient degradation in very deep convolutional neural networks (CNNs). Due to the strong results of ResNets, it is a natural choice to use features that it produces at various layers in transfer learning or for other feature extraction tasks. In order to analyse how the gradient degradation problem is solved by ResNets, we empirically investigate how discriminability changes as inputs propagate through the intermediate layers of two CNN variants: all-convolutional CNNs and ResNets. We found that the feature maps produced by residual-sum layers exhibit increasing discriminability with layer-distance from the input, but that feature maps produced by convolutional layers do not. We also studied how discriminability varies with training duration and the placement of convolutional layers. Our method suggests a way to determine whether adding extra layers will improve performance and show how gradient degradation impacts on which layers contribute increased discriminability.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, vol. 25, pp. 1097–1105, Lake Tahoe (2012)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning Representations, Banff (2014)
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., Rabinovich, A.: Going deeper with convolutions. In: The IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas (2015)
Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: International Conference on Artificial Intelligence and Statistics, Sardinia (2010)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas (2015)
Springenberg, J.T., Dosovitskiy, A., Brox, T., Riedmiller, M.: Striving for simplicity: the all convolutional net. In: Proceedings of International Conference on Learning Representations, San Diego (2015)
He, K., Zhang, X., Ren, S., Sun, J.: Identity mappings in deep residual networks. Preprint arXiv.1603.05027, Microsoft Research (2016)
Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: Proceedings of 32nd International Conference on Machine Learning, Lille (2015)
Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15, 1929–1958 (2015)
Velt, A., Wilber, M., Belongie, S.: Residual networks are exponential ensembles of relatively shallow networks. Preprint arXiv.1605.06431 (2016)
Zagoruyko, S., Komodakis, N.: Wide residual networks. Preprint arXiv.1605.07146 (2016)
Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks. In: European Conference on Computer Vision, Zurich (2014)
Sullivan, J., Razavian, A., Azizpour, H., Carlsson, S.: CNN features off-the-shelf: an astounding baseline for recognition. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 512–519, Columbus (2014)
McDonnell, M.D., Vladusich, T.: Enhanced image classification with a fast-learning shallow convolutional neural network. In: Proceedings of 2015 International Joint Conference on Neural Networks, Ireland (2015)
Guillaume, A., Bengio, Y.: Understanding intermediate layers using linear classifier probes. Preprint arXiv.1610.01644 (2016)
Huang, G.-B., Zhu, Q.-Y., Siew, C.-K.: Extreme learning machine: theory and applications. Neurocomputing 70, 489–501 (2006)
McDonnell, M.D., Tissera, M.D., Vladusich, T., van Schaik, A., Tapson, J.: Fast, simple and accurate handwritten digit classification by training shallow neural network classifiers with the extreme learning machine algorithm. PLoS One 10, 1–20 (2015). Article no. e0134254
Krizhevsky, A.: Learning multiple layers of features from tiny images. Ph.D. thesis, University of Toronto (2005)
Mohamed, A., Dahl, G.E., Hinton, G.E.: Deep belief networks for phone recognition. In: Workshop of Advances in Neural Information Processing Systems, Vancouver (2009)
Sainath, T.N., Weiss, R.J., Senior, A., Wilson, K.W., Vinyals, O.: Learning the speech front-end with raw waveform CLDNNs. In: Proceedings of Interspeech, Dresden (2015)
Loshchilov, I., Hutter, F.: SGDR: Stochastic gradient descent with restarts. Preprint arXiv.1608.03983 (2016)
Acknowledgements
This work is funded by Australian Government Research Training Program (RTP) Scholarship.
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
Gao, W., McDonnell, M.D. (2017). Analysis of Gradient Degradation and Feature Map Quality in Deep All-Convolutional Neural Networks Compared to Deep Residual Networks. In: Liu, D., Xie, S., Li, Y., Zhao, D., El-Alfy, ES. (eds) Neural Information Processing. ICONIP 2017. Lecture Notes in Computer Science(), vol 10635. Springer, Cham. https://doi.org/10.1007/978-3-319-70096-0_63
Download citation
DOI: https://doi.org/10.1007/978-3-319-70096-0_63
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-70095-3
Online ISBN: 978-3-319-70096-0
eBook Packages: Computer ScienceComputer Science (R0)