Skip to main content
SpringerLink
Log in

Visualizing Features on Classified Fauna Images Using Class Activation Maps

  • Conference paper
  • First Online:
Cooperative Design, Visualization, and Engineering (CDVE 2020)

Part of the book series: Lecture Notes in Computer Science ((LNISA,volume 12341))

Abstract

This article highlights first the power of deep learning in a collaborative context for the automatic extraction of information from images and complementarily the benefit of Class Activation Maps (CAM) for identifying in a visual way the features taken into account for extracting this information. Experimental results illustrate the approach as a whole on a significant challenge of classifying newt images.

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

Access this chapter

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 39.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
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

Institutional subscriptions

Notes

  1. 1.

    https://www.tensorflow.org/tutorials/images/transfer_learning.

  2. 2.

    https://amphibiaweb.org/species/4295.

  3. 3.

    https://keras.io/api/preprocessing/image/.

  4. 4.

    https://github.com/dyoann/CDVE2020/blob/master/train.py.

  5. 5.

    https://github.com/dyoann/CDVE2020/blob/master/cam.py.

References

  1. Dornelas, M., et al.: Quantifying temporal change in biodiversity: challenges and opportunities. Proc. Roy. Soc. B Biol. Sci. 280(1750) (2012)

    Google Scholar 

  2. Didry, Y., Mestdagh, X., Tamisier, T.: Newtrap: improving biodiversity surveys by enhanced handling of visual observations. In: Luo, Y. (ed.) CDVE 2019. LNCS, vol. 11792, pp. 277–281. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-30949-7_32

    Chapter  Google Scholar 

  3. Pan, S.J., Yang, Q.: A survey on transfer learning. IEEE Trans. Knowl. Data Eng. 22(10), 1345–1359 (2009)

    Article  Google Scholar 

  4. Ertam, F., Aydin, G.: Data classification with deep learning using TensorFlow. In: 2017 International Conference on Computer Science and Engineering (UBMK). IEEE (2017)

    Google Scholar 

  5. Tang: Intelligent Mobile Projects with TensorFlow. Packt Publishing, May 2018. Chapter 2. ISBN 9781788834544

    Google Scholar 

  6. Zhou, B., et al.: Learning deep features for discriminative localization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016)

    Google Scholar 

Download references

Acknowledgements

Thanks to Remy Haas and Lionel L’Hoste for retrieving the pictures on the field and annotating them in Newtrap Manager. We would like to thank the NVIDIA AI Technology Center Luxembourg for the fruitful discussions and technical advice. This work has been financed by the Luxembourg FNR through the POC17 NEWTRAP.

Author information

Authors and Affiliations

  1. Luxembourg Institute of Science and Technology (LIST), 41, rue du Brill, 4422, Belvaux, Luxembourg

    Yoanne Didry, Xavier Mestdagh & Thomas Tamisier

Authors
  1. Yoanne Didry
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Xavier Mestdagh
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Thomas Tamisier
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Yoanne Didry , Xavier Mestdagh or Thomas Tamisier .

Editor information

Editors and Affiliations

  1. University of the Balearic Islands, Palma, Mallorca, Spain

    Yuhua Luo

Rights and permissions

Reprints and permissions

Copyright information

© 2020 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Didry, Y., Mestdagh, X., Tamisier, T. (2020). Visualizing Features on Classified Fauna Images Using Class Activation Maps. In: Luo, Y. (eds) Cooperative Design, Visualization, and Engineering. CDVE 2020. Lecture Notes in Computer Science(), vol 12341. Springer, Cham. https://doi.org/10.1007/978-3-030-60816-3_38

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-60816-3_38

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-60815-6

  • Online ISBN: 978-3-030-60816-3

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation