Advertisement

Study of CNN Based Classification for Small Specific Datasets

  • Huu Ton LeEmail author
  • Thierry Urruty
  • Marie Beurton-Aimar
  • Thi Phuong Nghiem
  • Hoang Tung Tran
  • Romain Verset
  • Marie Ballere
  • Hien Phuong Lai
  • Muriel Visani
Chapter
Part of the Studies in Computational Intelligence book series (SCI, volume 769)

Abstract

Recently, deep learning and particularly, Convolutional Neural Network (CNN), has become predominant in many application fields, including visual image classification. In an applicative context of detecting areas with hazard of dengue fever, we propose a classification framework using deep neural networks on a limited dataset of images showing urban sites. For this purpose, we have to face multiple research issues: (i) small number of training data; (ii) images belonging to multiple classes; (iii) non-mutually exclusive classes. Our framework overcomes those issues by combining different techniques including data augmentation and multi-scale/region-based classification, in order to extract the most discriminative information from the data. Experiment results present our framework performance using several CNN architectures with different parameter sets, without and with transfer learning. Then, we analyze the effect of data augmentation and multiscale region based classification. Finally, we show that adding a classification weighting scheme allows the global framework to obtain more than 90% average precision for our classification task.

Keywords

CNN Image classification Small and dedicated dataset 

References

  1. 1.
    Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Pereira, F., Burges, C.J.C., Bottou, L., Weinberger, K.Q. (eds.), Advances in Neural Information Processing Systems, vol. 25, pp. 1097–1105. Curran Associates, Inc. (2012). http://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks.pdf
  2. 2.
    Lecun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436–444, 5 (2015)Google Scholar
  3. 3.
    Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. CoRR, vol. abs/1409.1556. http://arxiv.org/abs/1409.1556 (2014)
  4. 4.
    He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: surpassing human-level performance on imagenet classification. CoRR, vol. abs/1502.01852. http://arxiv.org/abs/1502.01852 (2015)
  5. 5.
    Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S.E., Anguelov, D., Erhan, D., Vanhoucke, V., Rabinovich, A.: Going deeper with convolutions. CoRR, vol. abs/1409.4842. http://arxiv.org/abs/1409.4842 (2014)
  6. 6.
    Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. CoRR, vol. abs/1502.03167. http://arxiv.org/abs/1502.03167 (2015)
  7. 7.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. CoRR, vol. abs/1512.03385. http://arxiv.org/abs/1512.03385 (2015)
  8. 8.
    Szegedy, C., Ioffe, S., Vanhoucke, V.: Inception-v4, inception-resnet and the impact of residual connections on learning. CoRR, vol. abs/1602.07261. http://arxiv.org/abs/1602.07261 (2016)
  9. 9.
    He, K., Zhang, X., Ren, S., Sun, J.: Identity mappings in deep residual networks. CoRR, vol. abs/1603.05027. http://arxiv.org/abs/1603.05027 (2016)
  10. 10.
    Razavian, A.S., Azizpour, H., Sullivan, J., Carlsson, S.: CNN features off-the-shelf: an astounding baseline for recognition. CoRR, vol. abs/1403.6382. http://arxiv.org/abs/1403.6382 (2014)
  11. 11.
    Long, M., Wang, J.: Learning transferable features with deep adaptation networks. CoRR, vol. abs/1502.02791. http://arxiv.org/abs/1502.02791 (2015)
  12. 12.
    Zheng, L., Yang, Y., Tian, Q.: SIFT meets CNN: a decade survey of instance retrieval. CoRR, vol. abs/1608.01807. http://arxiv.org/abs/1608.01807 (2016)
  13. 13.
    Babenko, A., Slesarev, A., Chigorin, A., Lempitsky, V.S.: Neural codes for image retrieval. CoRR, vol. abs/1404.1777. http://arxiv.org/abs/1404.1777 (2014)
  14. 14.
    Ren, S., He, K., Girshick, R.B., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. CoRR, vol. abs/1506.01497. http://arxiv.org/abs/1506.01497 (2015)
  15. 15.
    Erhan, D., Szegedy, C., Toshev, A., Anguelov, D.: Scalable object detection using deep neural networks. In: IEEE Conference on Computer Vision and Pattern Recognition, ser. CVPR ’14, pp. 2155–2162. IEEE Computer Society, Washington, DC, USA. http://dx.doi.org/10.1109/CVPR.2014.276 (2014)
  16. 16.
    Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. CoRR, vol. abs/1512.00567. http://arxiv.org/abs/1512.00567 (2015)
  17. 17.
    Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., Berg, A.C., Fei-Fei, L.: ImageNet large scale visual recognition challenge. International Journal of Computer Vision (IJCV) 115(3), 211–252 (2015)MathSciNetCrossRefGoogle Scholar
  18. 18.
    Lin, S., Zhao, Z., Su, F.: Homemade ts-net for automatic face recognition. In: Proceedings of the 2016 ACM on International Conference on Multimedia Retrieval, ser. ICMR ’16, pp. 135–142. ACM, New York, NY, USA. http://doi.acm.org/10.1145/2911996.2911999 (2016)
  19. 19.
    Margeta, J., Criminisi, A., Cabrera Lozoya, R., Lee, D.C., Ayache, N.: Fine-tuned convolutional neural nets for cardiac MRI acquisition plane recognition. Comput. Methods Biomech. Biomed. Eng. Im. Visual. https://hal.inria.fr/hal-01162880 Aug (2015)
  20. 20.
    14th International Workshop on Content-Based Multimedia Indexing, CBMI 2016. Bucharest, Romania, June 15–17, 2016. IEEE. http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=7496233 (2016)

Copyright information

© Springer International Publishing AG 2018

Authors and Affiliations

  • Huu Ton Le
    • 1
    Email author
  • Thierry Urruty
    • 2
  • Marie Beurton-Aimar
    • 3
  • Thi Phuong Nghiem
    • 1
  • Hoang Tung Tran
    • 1
  • Romain Verset
    • 4
  • Marie Ballere
    • 4
  • Hien Phuong Lai
    • 1
    • 5
  • Muriel Visani
    • 6
  1. 1.ICT LabUniversity of Science and Technology of Hanoi (USTH)Cau Giay, HanoiVietnam
  2. 2.XLIM, UMR CNRS 7252, University of PoitiersPoitiersFrance
  3. 3.LaBRI, University of BordeauxBordeauxFrance
  4. 4.ENSEEIHTToulouseFrance
  5. 5.M&S lab, UMI UMMISCO 209, IRDFCSE, Thuyloi UniversityHanoiVietnam
  6. 6.Laboratory L3iUniversity of La RochelleLa RochelleFrance

Personalised recommendations