Skip to main content
SpringerLink
Log in
Book cover

International Conference on Pattern Recognition

ICPR 2021: Pattern Recognition. ICPR International Workshops and Challenges pp 47–61Cite as

Samples Classification Analysis Across DNN Layers with Fractal Curves

  • Conference paper
  • First Online:

Part of the book series: Lecture Notes in Computer Science ((LNIP,volume 12663))

Abstract

Deep Neural Networks are becoming the prominent solution when using machine learning models. However, they suffer from a black-box effect that renders complicated their inner workings interpretation and thus the understanding of their successes and failures. Information visualization is one way among others to help in their interpretability and hypothesis deduction. This paper presents a novel way to visualize a trained DNN to depict at the same time its architecture and its way of treating the classes of a test dataset at the layer level. In this way, it is possible to visually detect where the DNN starts to be able to discriminate the classes or where it could decrease its separation ability (and thus detect an oversized network). We have implemented the approach and validated it using several well-known datasets and networks. Results show the approach is promising and deserves further studies.

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

Chapter
USD   29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD   84.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD   109.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Learn about institutional subscriptions

References

  1. Abadi, M., et al.: TensorFlow: large-scale machine learning on heterogeneous systems (2015). https://www.tensorflow.org/. Software available from tensorflow.org

  2. Fuad, K.A.A., Martin, P.E., Giot, R., Bourqui, R., Benois-Pineau, J., Zemmari, A.: Features understanding in 3D CNNs for actions recognition in video. In: The tenth International Conference on Image Processing Theory, Tools and Applications (IPTA 2020), p. 6 (2020)

    Google Scholar 

  3. Auber, D., Novelli, N., Melançon, G.: Visually mining the datacube using a pixel-oriented technique. In: 2007 11th International Conference Information Visualization (IV 2007), pp. 3–10. IEEE (2007)

    Google Scholar 

  4. Behrisch, M., Bach, B., Henry Riche, N., Schreck, T., Fekete, J.D.: Matrix reordering methods for table and network visualization. Comput. Graph. Forum 35(3), 693–716 (2016)

    Article  Google Scholar 

  5. Binder, A., Montavon, G., Lapuschkin, S., Müller, K.-R., Samek, W.: Layer-wise relevance propagation for neural networks with local renormalization layers. In: Villa, A.E.P., Masulli, P., Pons Rivero, A.J. (eds.) ICANN 2016. LNCS, vol. 9887, pp. 63–71. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-44781-0_8

    Chapter  MATH  Google Scholar 

  6. Blanchard, F., Herbin, M., Lucas, L.: A new pixel-oriented visualization technique through color image. Inf. Vis. 4(4), 257–265 (2005)

    Article  Google Scholar 

  7. Chollet, F., et al.: Keras (2015). https://keras.io

  8. Erhan, D., Bengio, Y., Courville, A., Vincent, P.: Visualizing higher-layer features of a deep network. Technical report, University of Montreal (2009)

    Google Scholar 

  9. Gardner, M.: Mathematical games-in which “monster” curves force redefinition of the word “curve”. Sci. Am. 235(6), 124–133 (1976)

    Article  Google Scholar 

  10. Ghazi, M.M., Yanikoglu, B., Aptoula, E.: Plant identification using deep neural networks via optimization of transfer learning parameters. Neurocomputing 235, 228–235 (2017)

    Article  Google Scholar 

  11. Halnaut, A., Giot, R., Bourqui, R., Auber, D.: Deep dive into deep neural networks with flows. In: 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, pp. 231–239 (2020)

    Google Scholar 

  12. He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)

    Google Scholar 

  13. Hilbert, D.: Über die stetige abbildung einer linie auf ein flächenstück. In: Dritter Band: Analysis Grundlagen der Mathematik Physik Verschiedenes, pp. 1–2. Springer (1935)

    Google Scholar 

  14. Hohman, F., Kahng, M., Pienta, R., Chau, D.H.: Visual analytics in deep learning: an interrogative survey for the next frontiers. IEEE Trans. Visual Comput. Graphics 25(8), 2674–2693 (2018)

    Article  Google Scholar 

  15. Kahng, M., Andrews, P.Y., Kalro, A., Chau, D.H.: ActiVis: visual exploration of industry-scale deep neural network models. IEEE Trans. Visual Comput. Graphics 24(1), 88–97 (2018)

    Article  Google Scholar 

  16. Kahng, M., Thorat, N., Chau, D.H.P., Viégas, F.B., Wattenberg, M.: GAN lab: understanding complex deep generative models using interactive visual experimentation. IEEE Trans. Visual Comput. Graphics 25(1), 1–11 (2018)

    Google Scholar 

  17. Keim, D.A.: Designing pixel-oriented visualization techniques: theory and applications. IEEE Trans. Visual Comput. Graphics 6(1), 59–78 (2000)

    Article  Google Scholar 

  18. LeCun, Y.: The MNIST database of handwritten digits (1998). http://yann.lecun.com/exdb/mnist/

  19. LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436–444 (2015)

    Article  Google Scholar 

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

    Article  Google Scholar 

  21. Liu, M., Liu, S., Su, H., Cao, K., Zhu, J.: Analyzing the noise robustness of deep neural networks. In: 2018 IEEE Conference on Visual Analytics Science and Technology (VAST), pp. 60–71. IEEE (2018)

    Google Scholar 

  22. Liu, M., Shi, J., Li, Z., Li, C., Zhu, J., Liu, S.: Towards better analysis of deep convolutional neural networks. IEEE Trans. Visual Comput. Graphics 23(1), 91–100 (2017)

    Article  Google Scholar 

  23. Maaten, L.v.d., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9, 2579–2605 (2008)

    Google Scholar 

  24. Meyer, M., Sedlmair, M., Quinan, P.S., Munzner, T.: The nested blocks and guidelines model. Inf. Vis. 14(3), 234–249 (2015)

    Article  Google Scholar 

  25. Morton, G.M.: A computer oriented geodetic data base and a new technique in file sequencing. Technical report, International Business Machines Company New York (1966)

    Google Scholar 

  26. Norton, A.P., Qi, Y.: Adversarial-playground: a visualization suite showing how adversarial examples fool deep learning. In: 2017 IEEE Symposium on Visualization for Cyber Security (VizSec), pp. 1–4. IEEE (2017)

    Google Scholar 

  27. Rauber, P.E., Fadel, S.G., Falcao, A.X., Telea, A.C.: Visualizing the hidden activity of artificial neural networks. IEEE Trans. Visual Comput. Graphics 23(1), 101–110 (2017)

    Article  Google Scholar 

  28. Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vision 115(3), 211–252 (2015)

    Article  MathSciNet  Google Scholar 

  29. Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-cam: visual explanations from deep networks via gradient-based localization. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 618–626 (2017)

    Google Scholar 

  30. d. Silva, L.E.B., Wunsch, D.C.: A study on exploiting vat to mitigate ordering effects in fuzzy art. In: 2018 International Joint Conference on Neural Networks (IJCNN), pp. 1–8 (2018)

    Google Scholar 

  31. Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. preprint arXiv:1409.1556 (2014)

  32. Smilkov, D., Carter, S., Sculley, D., Viégas, F.B., Wattenberg, M.: Direct-manipulation visualization of deep networks. arXiv preprint arXiv:1708.03788 (2017)

  33. Sugiyama, K., Tagawa, S., Toda, M.: Methods for visual understanding of hierarchical system structures. IEEE Trans. Syst. Man Cybern. 11, 109–125 (1981)

    Article  MathSciNet  Google Scholar 

  34. Tang, Y.: Deep learning using linear support vector machines. In: In ICML (2013)

    Google Scholar 

  35. Wang, J., Gou, L., Shen, H.W., Yang, H.: DQNViz: a visual analytics approach to understand deep q-networks. IEEE Trans. Visual Comput. Graphics 25(1), 288–298 (2019)

    Article  Google Scholar 

  36. Wang, Z.J., et al.: CNN 101: interactive visual learning for convolutional neural networks. In: Extended Abstracts of the 2020 CHI Conference on Human Factors in Computing Systems, pp. 1–7 (2020)

    Google Scholar 

  37. Wongsuphasawat, K., et al.: Visualizing dataflow graphs of deep learning models in TensorFlow. IEEE Trans. Visual Comput. Graphics 24(1), 1–12 (2017)

    Article  Google Scholar 

  38. Xiao, H., Rasul, K., Vollgraf, R.: Fashion-MNIST: a novel image dataset for benchmarking machine learning algorithms. arXiv preprint arXiv:1708.07747 (2017)

  39. Zhang, Q., Nian Wu, Y., Zhu, S.C.: Interpretable convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8827–8836 (2018)

    Google Scholar 

  40. Zhang, Q., Yang, Y., Ma, H., Wu, Y.N.: Interpreting CNNs via decision trees. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6261–6270 (2019)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Univ. Bordeaux, Bordeaux INP, CNRS, LaBRI, UMR5800, 33400, Talence, France

    Adrien Halnaut, Romain Giot, Romain Bourqui & David Auber

Authors
  1. Adrien Halnaut
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Romain Giot
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Romain Bourqui
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. David Auber
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Adrien Halnaut .

Editor information

Editors and Affiliations

  1. Dipartimento di Ingegneria dell’Informazione, University of Firenze, Firenze, Italy

    Alberto Del Bimbo

  2. Dipartimento di Ingegneria “Enzo Ferrari”, Università di Modena e Reggio Emilia, Modena, Italy

    Rita Cucchiara

  3. Department of Computer Science, Boston University, Boston, MA, USA

    Stan Sclaroff

  4. Dipartimento di Matematica e Informatica, University of Catania, Catania, Italy

    Giovanni Maria Farinella

  5. Cloud & AI, JD.COM, Beijing, China

    Tao Mei

  6. Dipartimento di Ingegneria dell’Informazione, University of Firenze, Firenze, Italy

    Marco Bertini

  7. Computational Sciences Department, National Institute of Astrophysics, Optics and Electronics (INAOE), Tonantzintla, Puebla, Mexico

    Hugo Jair Escalante

  8. Dipartimento di Ingegneria “Enzo Ferrari”, Università di Modena e Reggio Emilia, Modena, Italy

    Roberto Vezzani

Rights and permissions

Reprints and permissions

Copyright information

© 2021 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Halnaut, A., Giot, R., Bourqui, R., Auber, D. (2021). Samples Classification Analysis Across DNN Layers with Fractal Curves. In: Del Bimbo, A., et al. Pattern Recognition. ICPR International Workshops and Challenges. ICPR 2021. Lecture Notes in Computer Science(), vol 12663. Springer, Cham. https://doi.org/10.1007/978-3-030-68796-0_4

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-68796-0_4

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-68795-3

  • Online ISBN: 978-3-030-68796-0

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Societies and partnerships

Search

Navigation