Skip to main content
SpringerLink
Log in

Multipath feature recalibration DenseNet for image classification

  • Original Article
  • Published:
International Journal of Machine Learning and Cybernetics Aims and scope Submit manuscript

Abstract

Recently, deep neural networks have demonstrated their efficiency in image classification tasks, which are commonly achieved by an extended depth and width of network architecture. However, poor convergence, over-fitting and gradient disappearance might be generated with such comprehensive architectures. Therefore, DenseNet is developed to address these problems. Although DenseNet adopts bottleneck technique in DenseBlocks to avoid relearning feature-maps and decrease parameters, this operation may lead to the skip and loss of important features. Besides, it still takes oversized computational power when the depth and width of the network architecture are increased for better classification. In this paper, we propose a variate of DenseNet, named Multipath Feature Recalibration DenseNet (MFR-DenseNet), to stack convolution layers instead of adopting bottleneck for improving feature extraction. Meanwhile, we build multipath DenseBlocks with Squeeze-Excitation (SE) module to represent the interdependencies of useful feature-maps among different DenseBlocks. Experiments in CIFAR-10, CIFAR-100, MNIST and SVHN reveal the efficiency of our network, with further reduced redundancy whilst maintaining the high accuracy of DenseNet.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Similar content being viewed by others

References

  1. Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. Neural information processing systems. Springer, New York, pp 1097–1105

    Google Scholar 

  2. Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition. In: International conference on learning representations (ICLR)

  3. Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition(CVPR), pp 1–9

  4. Srivastava RK, Greff K, Schmidhuber J (2015) Training very deep networks. Advances in neural information processing systems. Springer, New York, pp 2377–2385

    Google Scholar 

  5. 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 (CVPR), pp 770–778

  6. Hochreiter S (1998) The vanishing gradient problem during learning recurrent neural nets and problem solutions. Int J Uncertain Fuzziness Knowl Based Syst 06(02):107–116

    Article  Google Scholar 

  7. Bengio Y (2002) Learning long-term dependencies with gradient descent is difficult. IEEE Trans Neural Netw Learn Syst 05(02):157–166

    Article  Google Scholar 

  8. Huang G, Liu Z, Laurens VDM, Weinberger KQ (2017) Densely connected convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp 4700–4708

  9. Liu W, Zeng K (2018) Sparsenet: a sparse DenseNet for image classification, arXiv. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR)

  10. Zhang K, Guo Y, Wang X, Yuan J, Ding Q (2019) Multiple feature reweight DenseNet for image classification. IEEE Access 7:9872–9880

    Article  Google Scholar 

  11. Zhang Z, Liang X, Dong X, Xie Y, Cao G (2018) A sparse-view CT reconstruction method based on combination of DenseNet and deconvolution. IEEE Trans Med Imaging 37(6):1407–1417

    Article  Google Scholar 

  12. Chen Y, Li J, Xiao H, Jin X, Yan S, Feng J (2017) Dual path networks. In: Neural information processing systems (NeurIPS), pp 4467–4475

  13. Lodhi B, Kang J (2019) Multipath-densenet: a supervised ensemble architecture of densely connected convolutional networks. Inf Sci 482:63–72

    Article  Google Scholar 

  14. Huang G, Liu S, Der Maaten LV, Weinberger KQ (2018) CondenseNet: an efficient DenseNet using learned group convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp 2752–2761

  15. Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. In: International conference on machine learning (ICML), pp 448–456

  16. Glorot X, Bordes A, Bengio Y (2011) Deep sparse rectifier neural networks. In: International conference on artificial intelligence and statistics, pp 315–323

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

    Article  Google Scholar 

  18. Hu J, Shen L, Sun G (2018) Squeeze-and-excitation networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp 7132–7141

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

  20. Deng L (2012) The MNIST database of handwritten digit images for machine learning research [best of the web]. IEEE Signal Process Mag 29(6):141–142

    Article  Google Scholar 

  21. 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 2011, [Online]. http://ufldl.stanford.edu/housenumbers/nips2011_housenumbers.pdf

  22. He K, Zhang X, Ren S, Sun J (2015) Delving deep into rectifiers: surpassing human-level performance on imagenet classification. In: The IEEE international conference on computer vision (ICCV), pp 1026–1034

  23. Lin M, Chen Q, Yan S (2014) Network in network. In: International conference on learning representations (ICLR)

  24. Larsson G, Maire M, Shakhnarovich G (2017) FractalNet: ultra-deep neural networks without residuals. In: International conference on learning representations (ICLR)

  25. Xie S, Girshick R, Dollar P, Tu Z, He K (2017) Aggregated residual transformations for deep neural networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp 5987–5995

  26. Zagoruyko S, Komodakis N (2016) Wide residual networks. In: Proceedings of the British Machine Vision Conference (BMVC), pp 87.1–87.12

  27. Sandler M, Howard A, Zhu M, Zhmoginov A, Chen LC (2019) Grading of hepatocellular carcinoma using 3D SE-DenseNet in dynamic enhanced MR images. Comput Biol Med 107:45–47

    Google Scholar 

Download references

Funding

This research is supported by the National Natural Science Foundation of China (Grant 61671152, 61901119).

Author information

Authors and Affiliations

  1. Fujian Key Lab for Intelligent Processing and Wireless Transmission of Media Information, College of Physics and Information Engineering, Fuzhou University, Fuzhou, 350116, Fujian, China

    Bolin Chen, Tiesong Zhao, Jiahui Liu & Liqun Lin

Authors
  1. Bolin Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Tiesong Zhao
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Jiahui Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Liqun Lin
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Liqun Lin.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

This research is supported by the National Natural Science Foundation of China (grant 61671152, 61901119).

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Chen, B., Zhao, T., Liu, J. et al. Multipath feature recalibration DenseNet for image classification. Int. J. Mach. Learn. & Cyber. 12, 651–660 (2021). https://doi.org/10.1007/s13042-020-01194-4

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s13042-020-01194-4

Keywords

Search

Navigation