In this work, instead of designing deeper convolutional neural networks, we investigate the relationship between the nonlinearity of convolution layer and the performance of the network. We modify the normal convolution layer by inserting quadratic convolution units which can map linear features to a higher-dimensional space in a single layer so as to enhance the approximability of the network. A genetic algorithm-based training scheme is adopted to reduce the time and space complexity caused by the quadratic convolution. Our method is experimented on classical image classification architectures including VGG-16 Net and GoogLeNet and outperforms the original models on the ImageNet classification dataset. The experimental results also show that better performance of our method can be achieved with a shallower architecture. We notice that VGG-16 model is widely used in popular object detection frameworks such as faster R-CNN and SSD. We adopt our modified VGG-16 model in these frameworks and also achieve improvements on PASCAL VOC2007 and VOC2012 dataset.
This is a preview of subscription content, log in to check access.
Buy single article
Instant access to the full article PDF.
Price includes VAT for USA
Subscribe to journal
Immediate online access to all issues from 2019. Subscription will auto renew annually.
This is the net price. Taxes to be calculated in checkout.
Abadi M, Agarwal A, Barham P, Brevdo E, Chen Z, Citro C, Corrado GS, Davis A, Dean J, Devin M et al (2016) Tensorflow: large-scale machine learning on heterogeneous distributed systems. arXiv preprint arXiv:1603.04467
Aizerman MA (1964) Theoretical foundations of the potential function method in pattern recognition learning. Autom Remote Control 25:821–837
Cho Y, Saul LK (2010) Large-margin classification in infinite neural networks. Neural Comput 22(10):2678–2697
Deng J, Dong W, Socher R, Li L-J, Li K, Fei-Fei L (2009) Imagenet: a large-scale hierarchical image database. In: IEEE conference on computer vision and pattern recognition, 2009. CVPR, 2009. IEEE, pp 248–255
Everingham M, Van Gool L, Williams CKI, Winn J, Zisserman A (2007) The PASCAL visual object classes challenge (VOC2007) results. http://www.pascal-network.org/challenges/VOC/voc2007/workshop/index.html. Accessed 1 Dec 2017
Everingham M, Van Gool L, Williams CKI, Winn J, Zisserman A (2012) The PASCAL visual object classes challenge (VOC2012) results. http://www.pascal-network.org/challenges/VOC/voc2012/workshop/index.html. Accessed 1 Dec 2017
Girshick R (2015) Fast r-cnn. arXiv preprint arXiv:1504.08083
Girshick R, Donahue J, Darrell T, Malik J (2014) 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
Glorot X, Bengio Y (2010) Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the 13th international conference on artificial intelligence and statistics, pp 249–256
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770–778
Holland JH (1992) Adaptation in natural and artificial systems: an introductory analysis with applications to biology, control and artificial intelligence. MIT Press, Cambridge
Horn RA (1990) The Hadamard product. In: Proceedings of symposia in applied mathematics, vol 40, pp 87–169
Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. In: International conference on machine learning, pp 448–456
Ji Y, Zhang H, Wu QMJ (2018) Salient object detection via multi-scale attention CNN. Neurocomputing 322:130–140
Jia Y, Shelhamer E, Donahue J, Karayev S, Long J, Girshick R, Guadarrama S, Darrell T (2014) Caffe: convolutional architecture for fast feature embedding. In: Proceedings of the 22nd ACM international conference on multimedia, pp 675–678
Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980
Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems, pp 1097–1105
LeCun Y, Boser B, Denker JS, Henderson D, Howard RE, Hubbard W, Jackel LD (1989) Backpropagation applied to handwritten zip code recognition. Neural Comput 1(4):541–551
Leshno M, Lin VY, Pinkus A, Schocken S (1993) Multilayer feedforward networks with a nonpolynomial activation function can approximate any function. Neural Netw 6(6):861–867
Lin T-Y, RoyChowdhury A, Maji S (2015) Bilinear CNN models for fine-grained visual recognition. In: Proceedings of the IEEE international conference on computer vision, pp 1449–1457
Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu C-Y, Berg AC (2016) Ssd: single shot multibox detector. In: European conference on computer vision. Springer, pp 21–37
Mairal J (2016) End-to-end kernel learning with supervised convolutional kernel networks. Advances in neural information processing systems pp 1399–1407
Mairal J, Koniusz P, Harchaoui Z, Schmid C (2014) Convolutional kernel networks. Advances in neural information processing systems, pp 2627–2635
Öztürk Ş, Akdemir B (2017) A convolutional neural network model for semantic segmentation of mitotic events in microscopy images. Neural Comput Appl. https://doi.org/10.1007/s00521-017-3333-9
Öztürk Ş, Akdemir B (2018) Effects of histopathological image pre-processing on convolutional neural networks. Procedia Comput Sci 132:396–403
Redmon J, Farhadi A (2017) Yolo9000: better, faster, stronger. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7263–7271
Redmon J, Divvala S, Girshick R, Farhadi A (2016) You only look once: unified, real-time object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 779–788
Ren S, He K, Girshick R, Sun J (2017) Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal Mach Intell 39(6):1137–1149
Russakovsky O, Deng J, Hao S, Krause J, Satheesh S, Ma S, Huang Z, Karpathy A, Khosla A, Bernstein M, Berg AC, Fei-Fei L (2015) ImageNet large scale visual recognition challenge. Int J Comput Vis (IJCV) 115(3):211–252. https://doi.org/10.1007/s11263-015-0816-y
Saxe AM, McClelland JL, Ganguli S (2013) Exact solutions to the nonlinear dynamics of learning in deep linear neural networks. arXiv preprint arXiv:1312.6120
Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556
Srivastava RK, Greff K, Schmidhuber J (2015) Training very deep networks. In: Advances in neural information processing systems, pp 2377–2385
Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A et al (2015) Going deeper with convolutions. In: CVPR
Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z (2016) Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2818–2826
Zhang H, Ji Y, Huang W, Liu L (2018) Sitcom-star-based clothing retrieval for video advertising: a deep learning framework. Neural Comput Appl. https://doi.org/10.1007/s00521-018-3579-x
This research was supported partly by National Key Research and Development Program of China 2016YFB0201304, National Natural Science Foundation of China (NSFC) Research Projects 61822402, 61774045, 61574046 and 61574044.
Conflict of interest
We declare that we have no financial and personal relationships with other people or organizations that can inappropriately influence our work, there is no professional or other personal interest of any nature or kind in any product, service and/or company that could be construed as influencing the position presented in, or the review of, the manuscript entitled.
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
About this article
Cite this article
Jiang, Y., Yang, F., Zhu, H. et al. Nonlinear CNN: improving CNNs with quadratic convolutions. Neural Comput & Applic 32, 8507–8516 (2020). https://doi.org/10.1007/s00521-019-04316-4
- Neural network
- Machine learning
- Quadratic convolution