Top

Published in:

2017 | OriginalPaper | Chapter

PreNet: Parallel Recurrent Neural Networks for Image Classification

Authors : Junbo Wang, Wei Wang, Liang Wang, Tieniu Tan

Published in: Computer Vision

Publisher: Springer Singapore

Activate our intelligent search to find suitable subject content or patents.

search-config

AI-assisted search

Off

Abstract

Convolutional Neural Networks (CNNs) have made outstanding achievements in computer vision, e.g., image classification and object detection, by modelling the receptive field of visual cortex with convolution and pooling operations. However, CNNs have ignored to model the long-range spatial contextual information in images. It has long been believed that recurrent neural networks (RNNs) can model temporal sequences well by virtue of horizontal connections, and have been successfully applied in speech recognition and language modelling. In this paper, we propose a hierarchical parallel recurrent neural network (PreNet) to model spatial context for image classification. In this network, when transforming the whole image into sequences in four directions, we adopt the way of row-by-row/column-by-column scanning instead of traditional pixel-by-pixel scanning, for the convenience of fast convolution implementation. Following the recurrent network, a max-pooling operation is used to reduce the dimensionality of the obtained feature maps. The resulting PreNet can be easily paralleled on GPUs. We evaluate the proposed PreNet on two public benchmark datasets: MNIST and CIFAR-10. The proposed model can achieve the state-of-the-art classification performance, which demonstrates the advantage of PreNet over many comparative CNN structures.

Dont have a licence yet? Then find out more about our products and how to get one now:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

über 102.000 Bücher
über 537 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Finance + Banking
Management + Führung
Marketing + Vertrieb
Maschinenbau + Werkstoffe
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

inform now

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 390 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Maschinenbau + Werkstoffe

Jetzt Wissensvorsprung sichern!

inform now

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 340 Zeitschriften

aus folgenden Fachgebieten:

Bauwesen + Immobilien
Business IT + Informatik
Finance + Banking
Management + Führung
Marketing + Vertrieb
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

inform now

previous chapter Saliency Detection via CNN Coarse Learning and Compactness Based ELM Refinement

next chapter Person Re-identification Based on Body Segmentation

Azzopardi, G., Petkov, N.: Trainable cosfire filters for keypoint detection and pattern recognition. IEEE Trans. Pattern Anal. Mach. Intell. 35(2), 490–503 (2013)CrossRef

Bengio, Y., Simard, P., Frasconi, P.: Learning long-term dependencies with gradient descent is difficult. IEEE Trans. Neural Netw. 5(2), 157–166 (1994)CrossRef

Cho, K., Van Merriënboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., Bengio, Y.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078 (2014)

Ciresan, D.C., Meier, U., Gambardella, L.M., Schmidhuber, J.: Deep big simple neural nets excel on handwritten digit recognition. CoRR abs/1003.0358 (2010). http://arxiv.org/abs/1003.0358

Danihelka, I., Wayne, G., Uria, B., Kalchbrenner, N., Graves, A.: Associative long short-term memory. arXiv preprint arXiv:1602.03032 (2016)

Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 580–587 (2014)

Goodfellow, I.J., Warde-Farley, D., Mirza, M., Courville, A., Bengio, Y.: Maxout networks. arXiv preprint arXiv:1302.4389 (2013)

Graham, B.: Fractional max-pooling. arXiv preprint arXiv:1412.6071 (2014)

Graham, B.: Spatially-sparse convolutional neural networks. arXiv preprint arXiv:1409.6070 (2014)

10.

Graves, A., Mohamed, A.R., Hinton, G.: Speech recognition with deep recurrent neural networks. In: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6645–6649. IEEE (2013)

11.

Graves, A.: Supervised sequence labelling. In: Graves, A. (ed.) Supervised Sequence Labelling with Recurrent Neural Networks. SCI, vol. 385, pp. 5–13. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-24797-2_2 CrossRef

12.

Graves, A., Schmidhuber, J.: Framewise phoneme classification with bidirectional LSTM and other neural network architectures. Neural Netw. 18(5), 602–610 (2005)CrossRef

13.

Graves, A., Schmidhuber, J.: Offline handwriting recognition with multidimensional recurrent neural networks. In: Advances in Neural Information Processing Systems, pp. 545–552 (2009)

14.

Graves, A., Wayne, G., Danihelka, I.: Neural turing machines. arXiv preprint arXiv:1410.5401 (2014)

15.

Hinton, G.E., Srivastava, N., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.R.: Improving neural networks by preventing co-adaptation of feature detectors. arXiv preprint arXiv:1207.0580 (2012)

16.

Huang, Y., Wang, W., Wang, L.: Bidirectional recurrent convolutional networks for multi-frame super-resolution. In: Advances in Neural Information Processing Systems, pp. 235–243 (2015)

17.

Huang, Y., Wang, W., Wang, L.: Video super-resolution via bidirectional recurrent convolutional networks. IEEE Trans. Pattern Anal. Mach. Intell. (2017)

18.

Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167 (2015)

19.

Iyyer, M., Boyd-Graber, J.L., Claudino, L.M.B., Socher, R., Daume III, H.: A neural network for factoid question answering over paragraphs. In: EMNLP, pp. 633–644 (2014)

20.

Kotsiantis, S., Kanellopoulos, D., Pintelas, P.: Data preprocessing for supervised leaning. Int. J. Comput. Sci. 1(2), 111–117 (2006)

21.

Krizhevsky, A., Hinton, G.: Learning multiple layers of features from tiny images (2009)

22.

Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097–1105 (2012)

23.

LeCun, Y., Bottou, L., Bengio, Y., Haner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)CrossRef

24.

Lee, C.Y., Xie, S., Gallagher, P., Zhang, Z., Tu, Z.: Deeply-supervised nets. arXiv preprint arXiv:1409.5185 (2014)

25.

Lin, M., Chen, Q., Yan, S.: Network in network. arXiv preprint arXiv:1312.4400 (2013)

26.

Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431–3440 (2015)

27.

Mairal, J., Koniusz, P., Harchaoui, Z., Schmid, C.: Convolutional kernel networks. In: Advances in Neural Information Processing Systems, pp. 2627–2635 (2014)

28.

Pascanu, R., Mikolov, T., Bengio, Y.: On the difficulty of training recurrent neural networks. arXiv preprint arXiv:1211.5063 (2012)

29.

Simard, P.Y., Steinkraus, D., Platt, J.C.: Best practices for convolutional neural networks applied to visual document analysis. In: Document Analysis and Recognition, p. 958. IEEE (2003)

30.

Snoek, J., Larochelle, H., Adams, R.P.: Practical Bayesian optimization of machine learning algorithms. In: Advances in Neural Information Processing Systems, pp. 2951–2959 (2012)

31.

Springenberg, J.T., Riedmiller, M.: Improving deep neural networks with probabilistic maxout units. arXiv preprint arXiv:1312.6116 (2013)

32.

Stollenga, M.F., Byeon, W., Liwicki, M., Schmidhuber, J.: Parallel multi-dimensional LSTM, with application to fast biomedical volumetric image segmentation. In: Advances in Neural Information Processing Systems, pp. 2980–2988 (2015)

33.

Su, H., Liu, F., Xie, Y., Xing, F., Meyyappan, S., Yang, L.: Region segmentation in histopathological breast cancer images using deep convolutional neural network. In: 2015 IEEE 12th International Symposium on Biomedical Imaging (ISBI), pp. 55–58. IEEE (2015)

34.

Sutskever, I., Martens, J., Dahl, G., Hinton, G.: On the importance of initialization and momentum in deep learning. In: Proceedings of the 30th International Conference on Machine Learning (ICML 2013), pp. 1139–1147 (2013)

35.

Visin, F., Kastner, K., Cho, K., Matteucci, M., Courville, A., Bengio, Y.: ReNet: a recurrent neural network based alternative to convolutional networks. arXiv preprint arXiv:1505.00393 (2015)

36.

Wan, L., Zeiler, M., Zhang, S., Cun, Y.L., Fergus, R.: Regularization of neural networks using dropconnect. In: Proceedings of the 30th International Conference on Machine Learning (ICML 2013), pp. 1058–1066 (2013)

37.

Zeiler, M.D., Fergus, R.: Stochastic pooling for regularization of deep convolutional neural networks. arXiv preprint arXiv:1301.3557 (2013)

Title: PreNet: Parallel Recurrent Neural Networks for Image Classification
Authors: Junbo Wang
Wei Wang
Liang Wang
Tieniu Tan
Publisher: Springer Singapore
Book: Computer Vision
Print ISBN: 978-981-10-7301-4

Electronic ISBN: 978-981-10-7302-1

Copyright Year: 2017
DOI: https://doi.org/10.1007/978-981-10-7302-1_38

Springer Professional

Abstract

Please log in to get access to your license.

Dont have a licence yet? Then find out more about our products and how to get one now:

Springer Professional "Wirtschaft+Technik"

Springer Professional "Technik"

Springer Professional "Wirtschaft"

Premium Partner