Skip to main content
Springer Nature Link
Log in

Parametric Surround Modulation Improves the Robustness of the Deep Neural Networks

  • Conference paper
  • First Online:
Robot Intelligence Technology and Applications 7 (RiTA 2022)

Part of the book series: Lecture Notes in Networks and Systems ((LNNS,volume 642))

  • 1127 Accesses

Abstract

In this study, we propose a bio-inspired deep neural network that is robust to classification tasks in an unstructured environment. Deep neural networks show high classification accuracy when training and testing data are independent and identically distributed. However, deep neural networks show significantly low classification accuracy on the corrupted data. In this study, we propose Parametric Surround Modulation for robust image classification. Surround modulation is an important biological mechanism of mammalian visual systems. It detects object boundaries, controls contrast gain, and perceives semantic features invariant to the environmental changes. Parametric Surround Modulation applies the surround modulation function to deep neural networks with trainable parameters. Parametric Surround Modulation is trained on ImageNet and the performance of the module is evaluated on the corrupted dataset, ImageNet-C. Experimental results show that the proposed Parametric Surround Modulation accurately performs image classification for the corrupted data.

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

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Hendrycks, D., Dietterich, T.: Benchmarking neural network robustness to common corruptions and perturbations. In: International Conference on Learning Representations (2019)

    Google Scholar 

  2. Hendrycks, D., Mu, N., Cubuk, D., Zoph, B., Gilmer, J., Lakshminarayanan, B.: Augmix: a simple data processing method to improve robustness and uncertainty. In: International Conference on Learning Representations (2020)

    Google Scholar 

  3. Benz, P., Zhang, C., Karjauv, A., Kweon, S.: Revisiting batch normalization for improving corruption robustness. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 494–503 (2021)

    Google Scholar 

  4. Dapello, J., Marques, T., Schrimpf, M., Geiger, F., Cox, D., DiCarlo, J.: Simulating a primary visual cortex at the front of CNNs improves robustness to image perturbations. In: Advances in Neural Information Processing Systems, pp. 13073–13087 (2020)

    Google Scholar 

  5. Hasani, H., Soleymani, M., Aghajan, H.: Surround modulation: a bio-inspired connectivity structure for convolutional neural networks. In: Advances in Neural Information Processing Systems (2019)

    Google Scholar 

  6. Huang, X., Rangel, M., Briggman, L., Wei, W.: Neural mechanisms of contextual modulation in the retinal direction selective circuit. Nat. Commun. 10(1), 1–15 (2019)

    Google Scholar 

  7. Huang, X., Rangel, M., Briggman, L., Wei, W.: Surround modulation in human vision unmasked by masking experiments. Nat. Neurosci. 3(7), 724–728 (2020)

    Google Scholar 

  8. Yu, C., Klein, A., Levi, M.: Surround modulation of perceived contrast and the role of brightness induction. J. Vis. 1(1), 3 (2001)

    Article  Google Scholar 

  9. Huang, X., Albright, D., Stoner, R.: Adaptive surround modulation in cortical area MT. Neuron 53(5), 761–770 (2017)

    Article  Google Scholar 

  10. DeAngelis, C., Freeman, D., Ohzawa, I.: Length and width tuning of neurons in the cat’s primary visual cortex. Neuron 53(5), 761–770 (2017)

    Google Scholar 

  11. Huang, X., Albright, D., Stoner, R.: Adaptive surround modulation in cortical area MT. J. Neurophysiol. 71(1), 347–374 (1994)

    Google Scholar 

  12. Sceniak, P., Hawken, J., Shapley, R.: Visual spatial characterization of macaque V1 neurons. J. Neurophysiol. 85(5), 1873–1887 (2001)

    Article  Google Scholar 

  13. Radosavovic, I., Kosaraju, P., Girshick, R., He, K., Dollár, P.: Designing network design spaces. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10428–10436 (2020)

    Google Scholar 

  14. He, K., Zhang, X., Ren, S., Sun, J.: Going deeper with convolutions. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)

    Google Scholar 

  15. Szegedy, C., et al.: Going deeper with convolutions. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1–9 (2015)

    Google Scholar 

  16. Krizhevsky, A., Sutskever, I., Hinton, E.: Imagenet classification with deep convolutional neural networks. Commun. ACM 60(6), 84–90 (2017)

    Article  Google Scholar 

Download references

Acknowledgement

This work was supported by Institute of Information & Communications Technology Planning & Evaluation (IITP) grant funded by Korea government (MSIT) (No. 2020-0-00440, Development of Artificial Intelligence Technology that Continuously Improves Itself as the Situation Changes in the Real World). The student is supported by the BK21 FOUR from the Ministry of Education (Republic of Korea).

Author information

Authors and Affiliations

  1. Urban Robotics Lab, School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Republic of Korea

    Wooju Lee & Hyun Myung

Authors
  1. Wooju Lee
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Hyun Myung
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Hyun Myung .

Editor information

Editors and Affiliations

  1. School of Information and Communication Technology, Griffith University, Southport, Australia

    Jun Jo

  2. Department of Aerospace Engineering, KAIST, Daejeon, Korea (Republic of)

    Han-Lim Choi

  3. School of Information and Communication Technology, Griffith University, Southport, Australia

    Marde Helbig

  4. Department of Mechanical Engineering, Ulsan National Institute of Science and Technology (UNIST), Ulsan, Korea (Republic of)

    Hyondong Oh

  5. Department of Mechanical Engineering, KAIST, Daejeon, Korea (Republic of)

    Jemin Hwangbo

  6. Department of Mechanical Engineering, KAIST, Daejeon, Korea (Republic of)

    Chang-Hun Lee

  7. School of Information and Communication Technology, Griffith University, Southport, Australia

    Bela Stantic

Rights and permissions

Reprints and permissions

Copyright information

© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Lee, W., Myung, H. (2023). Parametric Surround Modulation Improves the Robustness of the Deep Neural Networks. In: Jo, J., et al. Robot Intelligence Technology and Applications 7. RiTA 2022. Lecture Notes in Networks and Systems, vol 642. Springer, Cham. https://doi.org/10.1007/978-3-031-26889-2_25

Download citation

Publish with us

Policies and ethics