September 2024
Volume 24, Issue 10
Open Access
Vision Sciences Society Annual Meeting Abstract  |   September 2024
Investigating the impact of Gaussian noise on face recognition performance for humans and convolutional neural networks
Author Affiliations & Notes
  • Ikhwan Jeon
    Vanderbilt University
  • Connor Parde
    University of California, Berkeley
  • Frank Tong
    Columbia University
  • Footnotes
    Acknowledgements  Supported by NIH grants R01EY029278 and R01EY035157 to FT.
Journal of Vision September 2024, Vol.24, 1506. doi:https://doi.org/10.1167/jov.24.10.1506
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Ikhwan Jeon, Connor Parde, Frank Tong; Investigating the impact of Gaussian noise on face recognition performance for humans and convolutional neural networks. Journal of Vision 2024;24(10):1506. https://doi.org/10.1167/jov.24.10.1506.

      Download citation file:


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

      ×
  • Supplements
Abstract

Recent work has shown that convolutional neural networks (CNNs) perform worse than human observers at recognizing objects presented with superimposed Gaussian noise, indicating poor alignment between CNN models and humans (Jang et al., 2021). However, it is unknown whether Gaussian noise might also disproportionately impair CNNs at tasks of face recognition, which more-heavily rely on the processing of lower-spatial-frequency information. We evaluated humans and face-trained CNNs using face images with varying levels of Gaussian noise, where noise intensity was specified by the signal to signal-plus-noise ratio (SSNR). Human participants completed a face-recognition task wherein they viewed face images of 10 different celebrities (80 images/celebrity) in an intermixed, randomized order, and were instructed to select the identity shown in each image. Each face image was presented for 200ms at a randomly-assigned SSNR level (SSNR = 0.1, 0.15, 0.2, 0.25, 0.3, 0.4, 0.5, 0.6, 0.8, or 1). Then, the same set of face images was presented to a face-classification trained version of AlexNet. The identity response from the CNN was indicated by the identity node for which each input image elicited the highest response. Performance for both human participants and the CNN was quantified by accuracy as a function of SSNR and was compared to the results of object recognition (Jang et al. 2021). Overall, humans exhibited better performance than the CNNs. But both humans and the CNNs better performed in face recognition than object recognition (SSNR thresholds of human: 0.17 for faces, 0.26 for objects; of CNNs: 0.25 for faces, 0.5 for objects). Moreover, face-trained model performance appeared highly similar to human, suggesting similar degrees of robustness to Gaussian visual noise. The fact that face-trained CNNs provide a reasonable account of human recognition of noisy face images may suggest that these CNNs are fairly aligned with the human face recognition system.

×
×

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.

×