Abstract
The main drawbacks of traditional densely connected convolution networks (DenseNet) lie in: complex network models, excessive parameters, a large amount of computational and storage resources, falling into the problem of over-fitting, resulting in low object recognition accuracy. In addition, in the field of fine-grained image classification, the recognition performance is insufficient due to the inadequate representation capability of extracting features. In order to cope with these problems, we propose a novel shallow densely connected convolution networks (called DenseNet-S), it works as: (1) we adopt a shallow network training strategy to degrade the computational complexity and reduce the parameters, in order to avoid excessive number of layers affecting the recognition accuracy; (2) we propose a novel squeeze method to further reduce the network parameters and effectively alleviate the over-fitting phenomena. In addition, we apply the fire module and add the squeeze layer and the expand layer to the convolution module in DenseNet; (3) we employ the factorization technique into small convolutions, which can partition a large two-dimensional convolution into two small one-dimensional convolutions, in order to improve the feature extraction capability and the recognition performance in fine-grained image classification. The effectiveness of DenseNet-S was evaluated by extensive experiments on three benchmark datasets including CIFAR-10, CIFAR-100 and SVHN.
Similar content being viewed by others
References
Lecun Y, Boser B, Denker J, Henderson D (1989) Backpropagation applied to handwritten zip code recognition. Neural Comput 1(4):541–551
Lecun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278–2324
Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: International conference on neural information processing systems, pp 1097–1105
Ren S, He K, Girshick R, Sun J (2015) Faster r-CNN: towards real-time object detection with region proposal networks. In: International conference on neural information processing systems, pp 91–99
Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation. In: IEEE conference on computer vision and pattern recognition, pp 3431–3440
Glorot X, Bordes A, Bengio Y (2011) Deep sparse rectifier neural networks. In: Proceedings of the fourteenth international conference on artificial intelligence and statistics, pp 315–323
Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. pp 1–14, CoRR, arXiv:1409.1556
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. pp 770–778
Huang G, Sun Y, Liu Z, Sedra D, Weinberger KQ (2016) Deep networks with stochastic depth. pp 646–661
He K, Zhang X, Ren S, Sun J (2016) Identity mappings in deep residual networks. In: European conference on computer vision, Springer, pp 630–645
Huang G, Liu Z, Van Der Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. In: IEEE conference on computer vision and pattern recognition, pp 2261–2269
Lin M, Chen Q, Yan S (2013) Network in network. pp 1–10, arXiv:1312.4400
Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D (2014) Vincent vanhoucke, and andrew rabinovich. Going deeper with convolutions, pp 1–9
Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z (2016) Rethinking the inception architecture for computer vision. In: IEEE conference on computer vision and pattern recognition, pp 2818–2826
Chollet F (2017) Xception: Deep learning with depthwise separable convolutions. arXiv preprint pp 1610–02357
Sifre L, Mallat S (2014) Rigid-motion scattering for image classification. PhD thesis, Citeseer
Howard AG, Zhu M, Chen B, Kalenichenko D, Wang W, Weyand T, Andreetto M, Adam H (2017) Mobilenets: Efficient convolutional neural networks for mobile vision applications. pp 1–9, arXiv:1704.04861
Zhang X, Zhou X, Lin M, Sun J (2017) ShuffleNet: An extremely efficient convolutional neural network for mobile devices. pp 1–9, arXiv:1707.01083
Iandola FN, Han S, Moskewicz MW, Ashraf K, Dally WJ, Keutzer K (2016) SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and 0.5mb model size. pp 1–13, arXiv:1602.07360
Deng J, Dong W, Socher R, Li J (2009) ImageNet: A large-scale hierarchical image database. In: 2009. CVPR 2009. IEEE conference on computer vision and pattern recognition, pp 248–255
Krizhevsky A, Hinton GE (2009) Learning multiple layers of features from tiny images. Technical report, Citeseer
Netzer Y, Wang T, Coates A, Bissacco A, Wu B, Ng AY (2011) Reading digits in natural images with unsupervised feature learning. In: NIPS workshop on deep learning and unsupervised feature learning, vol 2011, pp 5
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
Gross S, Wilber M (2016) Training and investigating residual nets. Facebook AI Research, CA.[Online]. Avilable: http://torch.ch/blog/2016/02/04/resnets. html
Sutskever I, Martens J, Dahl G, Hinton G (2013) On the importance of initialization and momentum in deep learning. In: International conference on machine learning, pp 1139–1147
Malinowski M, Fritz M (2013) Learnable pooling regions for image classification. pp 1–10, arXiv:1301.3516
Zeiler Matthew D, Fergus R (2013) Stochastic pooling for regularization of deep convolutional neural networks. pp 1–9, arXiv:1301.3557
Srivastava N (2013) Improving neural networks with dropout. University of Toronto 182:566
Snoek J, Larochelle H, Adams RP (2012) Practical bayesian optimization of machine learning algorithms. In: Advances in neural information processing systems, pp 2951–2959
Goodfellow IJ, Warde-Farley D, Mirza M, Courville A, Bengio Y (2013) Maxout networks. pp 1–9, arXiv:1302.4389
Srivastava N, Salakhutdinov RR (2013) Discriminative transfer learning with tree-based priors. In: Advances in neural information processing systems, pp 2094–2102
Goodfellow IJ, Bulatov Y, Ibarz J, Arnoud S, Shet V (2013) Multi-digit number recognition from street view imagery using deep convolutional neural networks. pp 1–13, arXiv:1312.6082
Larsson G, Maire M, Shakhnarovich G (2016) Fractalnet: Ultra-deep neural networks without residuals. pp 1–11, arXiv:1605.07648
Springenberg JT, Dosovitskiy A, Brox T, Riedmiller M (2014) Striving for simplicity: The all convolutional net. pp 1–14, arXiv:1412.6806
Lee C-Y, Xie S, Gallagher P, Zhang Z, Tu Z (2015) Deeply-supervised nets. pp 562–570
Yang Y, Zhong Z, Shen T, Lin Z (2018) Convolutional neural networks with alternately updated clique. In: IEEE conference on computer vision and pattern recognition, pp 2413–2422
Hudson DA, Manning CD (2018) Compositional attention networks for machine reasoning. pp 1–20, arXiv:1803.03067
Author information
Authors and Affiliations
Corresponding authors
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
This work is partially supported by the National Natural Science Foundation of China under Grant Nos. 61772091, 61802035; the Natural Science Foundation of Guangxi under Grant Nos. 2018GX NSFDA138005, 2016GXNSFAA380209, 2014GXNSFDA118037; the Project of Scientific Research and Technology Development in Guangxi under Grant Nos. AA18118047, AB16380272, AD18126015, 20175177; the Innovation Project of Guangxi Graduate Education under Grant No. YCSW2017187; the Sichuan Science and Technology Program under Grant Nos. 2018JY0448, 2019YFG0106, 2019YFS0067; the Innovative Research Team Construction Plan in Universities of Sichuan Province under Grant No. 18TD0027; the Scientific Research Foundation for Young Academic Leaders of Chengdu University of Information Technology under Grant No. J201701.
Rights and permissions
About this article
Cite this article
Yuan, C., Wu, Y., Qin, X. et al. An effective image classification method for shallow densely connected convolution networks through squeezing and splitting techniques. Appl Intell 49, 3570–3586 (2019). https://doi.org/10.1007/s10489-019-01468-7
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-019-01468-7