Abstract
Recent advances in image classification have been achieved with deep convolutional neural networks (CNNs). The pooling and sub-sampling operations in the CNNs introduce invariance to local transformations, but result in accuracy loss in the image applications. In this paper, we propose a novel deep network called “Weighted Integration Architecture Network” (WIAN) which can effectively recover the information loss due to the pooling operation in the CNNs. The proposed WIAN reuses the information from the previous layers in the network and assigns a weight to each according to the responses or entropy in the layer and then element-wise summing them to further enhance the image classification performance. Exhaustive experiments on four standard benchmark datasets (CIFAR-10, CIFAR-100, MNIST and SVHN) demonstrate the effectiveness as well as an improved performance of WIAN.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Krizhevsky, A., Hinton, G.: Learning multiple layers of features from tiny images (2009)
He, K., et al.: Delving deep into rectifiers: surpassing human-level performance on imagenet classification. In: Proceedings of the IEEE International Conference on Computer Vision (2015)
Lin, M., Chen, Q., Yan, S.: Network in network. arXiv preprint arXiv:1312.4400 (2013)
Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8689, pp. 818–833. Springer, Heidelberg (2014). doi:10.1007/978-3-319-10590-1_53
Srivastava, N., et al.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929–1958 (2014)
Szegedy, C., et al.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2015)
Lee, C.-Y., et al.: Deeply-supervised nets. arXiv preprint arXiv:1409.5185 (2014)
Bromley, J., et al.: Signature verification using a Siamese time delay neural network. Int. J. Pattern Recogn. Artif. Intell. 7(04), 669–688 (1993)
Hoffer, E., Ailon, N.: Deep metric learning using triplet network. In: Feragen, A., Pelillo, M., Loog, M. (eds.) SIMBAD 2015. LNCS, vol. 9370, pp. 84–92. Springer, Heidelberg (2015). doi:10.1007/978-3-319-24261-3_7
Sun, Y., Wang, X., Tang, X.: Deep convolutional network cascade for facial point detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2013)
Tompson, J., et al.: Efficient object localization using convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2015)
Yang, S., Ramanan, D.: Multi-scale recognition with DAG-CNNs. In: Proceedings of the IEEE International Conference on Computer Vision (2015)
Lin, M., et al.: Multiple feature fusion via weighted entropy for visual tracking. In: Proceedings of the IEEE International Conference on Computer Vision (2015)
Jia, Y., et al.: Caffe: convolutional architecture for fast feature embedding. In: Proceedings of the ACM International Conference on Multimedia. ACM (2014)
LeCun, Y., et al.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)
Netzer, Y., et al.: Reading digits in natural images with unsupervised feature learning. In: NIPS Workshop on Deep Learning and Unsupervised Feature Learning, Granada, Spain, vol. 2011 (2011)
Acknowledgments
This work was supported by the LIACS Media Lab at Leiden University. We are also grateful to the support of NVIDIA for this work.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing AG
About this paper
Cite this paper
Wu, S., Lew, M.S. (2016). Comparison of Information Loss Architectures in CNNs. In: Chen, E., Gong, Y., Tie, Y. (eds) Advances in Multimedia Information Processing - PCM 2016. PCM 2016. Lecture Notes in Computer Science(), vol 9917. Springer, Cham. https://doi.org/10.1007/978-3-319-48896-7_34
Download citation
DOI: https://doi.org/10.1007/978-3-319-48896-7_34
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-48895-0
Online ISBN: 978-3-319-48896-7
eBook Packages: Computer ScienceComputer Science (R0)