Skip to main content
SpringerLink
Log in

An improved residual network model for image recognition using a combination of snapshot ensembles and the cutout technique

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

NUF-Net (Naresuan University and Fiber One Public Company Limited Network) is a new and improved Convolutional Neural Network (CNN) model based on the previously developed NU-LiteNet model. Improvements in accuracy were achieved by adding the identity mapping technique of the ResNet model and incorporating Snapshot Ensembles and the Cutout technique into the NU-LiteNet model. We modified the structure of the convolution layers by changing any filters of a size larger than 3 ×3, into a 3 ×3 filter, thereby significantly reducing processing time and reducing the error rate. To test the effectiveness of our modifications, we developed 10 variations of the NUF-Net-Residual model, one of which, termed NUF-Net-Residual-102, achieved significantly lower error rates than both ResNet and Wide-ResNet when using CIFAR-10, CIFAR-100 and Tiny-ImageNet datasets. The relative error rates were 2.94% for CIFAR-10, 17.57% for CIFAR-100 and 29.57% for Tiny-ImageNet. As well, NUF-Net-Residual-102 achieved a model parameter size of 31.65 million which is a lower value than for Wide-ResNet-32 (46.16 million), although higher than ResNet-1202 (19.42 million).

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
Fig. 7
Fig. 8
Fig. 9
Fig. 10

Similar content being viewed by others

References

  1. Cheng G, Yang C, Yao X, Guo L, Han J (2018) When deep learning meets metric learning: Remote sensing image scene classification via learning discriminative CNNs. IEEE transactions on geoscience and remote sensing 56(5):2811–2821

    Article  Google Scholar 

  2. Chollet F (2017) Xception: Deep learning with depthwise separable convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1251–1258

  3. DeVries T, Taylor GW (2017) Improved regularization of convolutional neural networks with cutout. arXiv preprint arXiv:1708.04552

  4. El-Rahiem BA, Ahmed MAO, Reyad O, El-Rahaman HA, Amin M, El-Samie FA (2019) An efficient deep convolutional neural network for visual image classification. In: International conference on advanced machine learning technologies and applications. Springer, pp 23–31

  5. Gad R, Talha M, El-Latif AAA, Zorkany M, Ayman ES, Nawal EF, Muhammad G (2018) Iris recognition using multi-algorithmic approaches for cognitive internet of things (ciot) framework. Futur Gener Comput Syst 89:178–191

    Article  Google Scholar 

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

  7. Han D, Kim J, Kim J (2017) Deep pyramidal residual networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5927–5935

  8. 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

  9. 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

  10. Huang G, Li Y, Pleiss G, Liu Z, Hopcroft JE, Weinberger KQ (2017) Snapshot ensembles: Train 1, get m for free. arXiv preprint arXiv:1704.00109

  11. Huang G, Liu Z, Van Der Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4700–4708

  12. Iandola FN, Han S, Moskewicz MW, Ashraf K, Dally WJ, Keutzer K (2016) Squeezenet: Alexnet-level accuracy with 50x fewer parameters and 0.5 mb model size. arXiv preprint arXiv:1602.07360

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

  14. Kim Y, Hwang I, Cho NI (2017) A new convolutional network-in-network structure and its applications in skin detection, semantic segmentation, and artifact reduction. arXiv preprint arXiv:1701.06190

  15. Krizhevsky A, Hinton G, et al. (2009) Learning multiple layers of features from tiny images. Tech. rep., Citeseer

  16. Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems, pp 1097–1105

  17. Lee CY, Xie S, Gallagher P, Zhang Z, Tu Z (2015) Deeply-supervised nets. In: Artificial intelligence and statistics, pp 562–570

  18. Li K, Cheng G, Bu S, You X (2017) Rotation-insensitive and context augmented object detection in remote sensing images. IEEE Trans Geosci Remote Sens 56(4):2337–2348

    Article  Google Scholar 

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

  20. Loshchilov I, Hutter F (2016) Sgdr: Stochastic gradient descent with warm restarts. arXiv preprint arXiv:1608.03983

  21. Peng J, Li Q, El-Latif AAA, Wang N, Niu X (2013) Finger vein recognition with gabor wavelets and local binary patterns. IEICE Trans Inf Sys 96 (8):1886–1889

    Article  Google Scholar 

  22. Powers DM (2011) Evaluation: from precision, recall and f-measure to roc, informedness, markedness and correlation

  23. Romero A, Ballas N, Kahou SE, Chassang A, Gatta C, Bengio Y (2014) Fitnets: Hints for thin deep nets. arXiv preprint arXiv:1412.6550

  24. Shin HC, Roth HR, Gao M, Lu L, Xu Z, Nogues I, Yao J, Mollura D, Summers RM (2016) Deep convolutional neural networks for computeraided detection: Cnn architectures, dataset characteristics and transfer learning. IEEE Trans Med Imaging 35(5):1285–1298

    Article  Google Scholar 

  25. Srivastava RK, Greff K, Schmidhuber J (2015) Highway networks. arXiv preprint arXiv:1505.00387

  26. Szegedy C, Ioffe S, Vanhoucke V, Alemi AA (2017) Inception-v4, inception-resnet and the impact of residual connections on learning. In: Thirty-first AAAI conference on artificial intelligence

  27. 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, pp 1–9

  28. Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z (2016) .. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2818–2826

  29. Termritthikun C, Jamtsho Y, Muneesawang P (2019) On-device facial verification using NUF-Net model of deep learning. Engineering Applications of Artificial Intelligence 85:579–589

    Article  Google Scholar 

  30. Termritthikun C, Kanprachar S (2017) Accuracy improvement of thai food image recognition using deep convolutional neural networks. In: 2017 International electrical engineering congress (iEECON). IEEE, pp 1–4

  31. Termritthikun C, Kanprachar S (2018) Nu-resnet: Deep residual networks for thai food image recognition. Journal of Telecommunication, Electronic and Computer Engineering (JTEC) 10(1–4):29–33

    Google Scholar 

  32. Termritthikun C, Kanprachar S, Muneesawang P (2019) NU-LiteNet: Mobile Landmark Recognition using Convolutional Neural Networks. ECTI Transactions on Computer and Information Technology (ECTI-CIT) 13(1):21–28

    Google Scholar 

  33. Termritthikun C, Muneesawang P, Kanprachar S (2017) Nu-innet: Thai food image recognition using convolutional neural networks on smartphone. Journal of Telecommunication, Electronic and Computer Engineering (JTEC) 9(2-6):63–67

    Google Scholar 

  34. Wang N, Li Q, El-Latif AAA, Peng J, Niu X (2014) An enhanced thermal face recognition method based on multiscale complex fusion for gabor coefficients. Multimed Tools Appl 72(3):2339–2358

    Article  Google Scholar 

  35. Wang N, Li Q, El-Latif AAA, Zhang T, Niu X (2014) Toward accurate localization and high recognition performance for noisy iris images. Multimed Tools Appl 71(3):1411–1430

    Article  Google Scholar 

  36. Xie S, Girshick R, Dollár 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, pp 1492–1500

  37. Zagoruyko S, Komodakis N (2016) Wide residual networks. arXiv preprint arXiv:1605.07146

  38. Zagoruyko S, Komodakis N (2017) Diracnets: Training very deep neural networks without skipconnections. arXiv preprint arXiv:1706.00388

  39. Zhang K, Zhang Z, Li Z, Qiao Y (2016) Joint face detection and alignment using multitask cascaded convolutional networks. IEEE Signal Process Lett 23(10):1499–1503

    Article  Google Scholar 

  40. Zhong Z, Zheng L, Kang G, Li S, Yang Y (2017) Random erasing data augmentation. arXiv preprint arXiv:1708.04896

Download references

Acknowledgements

The authors would like to acknowledge the financial support from the Thailand Research Fund through the Royal Golden Jubilee Ph.D. Program (Grant No. PHD/0101/2559). We would also like to extend our appreciation to Mr. Roy I. Morien of the Naresuan University Graduate School for his assistance in editing the English grammar and expression in the paper.

Author information

Authors and Affiliations

  1. Faculty of Engineering, Department of Electrical and Computer Engineering, Naresuan University, Phitsanulok, 65000, Thailand

    Chakkrit Termritthikun, Yeshi Jamtsho & Paisarn Muneesawang

Authors
  1. Chakkrit Termritthikun
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yeshi Jamtsho
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Paisarn Muneesawang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Chakkrit Termritthikun.

Additional information

Publisher’s note

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

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Termritthikun, C., Jamtsho, Y. & Muneesawang, P. An improved residual network model for image recognition using a combination of snapshot ensembles and the cutout technique. Multimed Tools Appl 79, 1475–1495 (2020). https://doi.org/10.1007/s11042-019-08332-3

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-019-08332-3

Keywords

Search

Navigation