September 2024
Volume 24, Issue 10
Open Access
Vision Sciences Society Annual Meeting Abstract  |   September 2024
Spatial Frequency Decoupling: Bio-inspired strategy for Network Robustness
Author Affiliations & Notes
  • Suayb Arslan
    Massachusetts Institute of Technology
  • Michal Fux
    Massachusetts Institute of Technology
  • Hojin Jang
    Massachusetts Institute of Technology
  • Matt Groth
    Massachusetts Institute of Technology
  • Joydeep Munshi
    GE Research
  • Walt Dixon
    GE Research
  • Pawan Sinha
    Massachusetts Institute of Technology
  • Footnotes
    Acknowledgements  This research is supported by ODNI, IARPA. The views are of the authors and shouldn't be interpreted as representing official policies of ODNI, IARPA, or the U.S. Gov., which is authorized to reproduce & distribute reprints for governmental purposes notwithstanding any copyright annotation therein.
Journal of Vision September 2024, Vol.24, 1283. doi:https://doi.org/10.1167/jov.24.10.1283
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Suayb Arslan, Michal Fux, Hojin Jang, Matt Groth, Joydeep Munshi, Walt Dixon, Pawan Sinha; Spatial Frequency Decoupling: Bio-inspired strategy for Network Robustness. Journal of Vision 2024;24(10):1283. https://doi.org/10.1167/jov.24.10.1283.

      Download citation file:


      © ARVO (1962-2015); The Authors (2016-present)

      ×
  • Supplements
Abstract

Convolutional Neural Networks (CNNs) are known to have an inherent bias towards texture and reliance on high spatial frequency elements. These characteristics compromise their classification robustness. How might we incorporate global shape information in the classification pipeline of such networks to capture long-range dependencies? Our electrophysiological studies with human participants provide some clues. We devised an experiment involving high-density EEG measurements from ten participants exposed to low-spatial frequency, high-spatial frequency, and full-resolution images comprising objects and faces. Analyses revealed an unexpected temporal staggering of high versus low spatial frequencies. Decoding of neural information to infer stimulus identity was feasible earlier in the timeline with low spatial frequencies than with high spatial frequencies. These findings have helped us formulate an analogous strategy of spatial frequency decoupling and temporal staging in convolutional network architectures. We find that CNNs endowed with this biologically-inspired feature in their architectural bias demonstrate superior resilience against challenging scenarios, such as viewpoint changes and turbulence. Based on these results, we propose that a staggered feedforward processing sequence, progressing from low to high frequencies, may be an important property to boost network resilience and secure effective out-of-distribution generalization.

×
×

This PDF is available to Subscribers Only

Sign in or purchase a subscription to access this content. ×

You must be signed into an individual account to use this feature.

×