December 2022
Volume 22, Issue 14
Open Access
Vision Sciences Society Annual Meeting Abstract  |   December 2022
Interpretable object dimensions in deep neural networks and their similarities to human representations
Author Affiliations & Notes
  • Lukas Muttenthaler
    Max Planck Institute for Human Cognitive and Brain Sciences
    Technical University of Berlin
  • Martin N. Hebart
    Max Planck Institute for Human Cognitive and Brain Sciences
  • Footnotes
    Acknowledgements  This work was supported by a Max Planck Research Group grant of the Max Planck Society awarded to MNH
Journal of Vision December 2022, Vol.22, 4516. doi:https://doi.org/10.1167/jov.22.14.4516
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Lukas Muttenthaler, Martin N. Hebart; Interpretable object dimensions in deep neural networks and their similarities to human representations. Journal of Vision 2022;22(14):4516. https://doi.org/10.1167/jov.22.14.4516.

      Download citation file:


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

      ×
  • Supplements
Abstract

Convolutional neural networks (CNNs) have recently received a lot of attention in the vision sciences as candidate models of core visual object recognition. At the behavioral level, these models show near-human object classification performance, allow for oftentimes excellent prediction of object-related choices, and explain significant proportions of variance in object similarity judgments. Despite these parallels, CNNs continue to exhibit a performance gap in explaining object-based representations and behavior. Here we aimed at identifying what factors determine the similarities and differences between CNN and human object representations. Paralleling object similarity judgments in humans, we generated 20 million in-silico triplet odd-one-out choices on 22,248 natural object images, using the penultimate layer activations of a pretrained VGG-16 model. Next, we applied a gradient-based similarity embedding technique that yielded 57 sparse, non-negative dimensions that were hi ghly predictive of the CNN’s odd-one-out choices. These dimensions were interpretable, reflecting properties of objects that are both visual (e.g. color, shape, texture) and conceptual (e.g. high-level category, value) in nature. While recent work indicated that CNNs respond to the texture of an object rather than its shape, our results reveal robust shape-related dimensions, indicating that texture bias may not be a general representational limitation. To probe the representational content of individual dimensions, we developed a dimension prediction approach, allowing us to (1) generate optimal stimuli for individual dimensions, (2) reveal image regions for driving these dimensions, and (3) causally manipulate individual image features to identify the dimensions’ representational nature. Despite strong parallels between CNNs and humans, a one-to-one mapping of CNN dimensions to human representational dimensions revealed striking differences for a subset of images, reve aling novel image biases that limit a CNNs generalization ability. Together, this interpretability technique offers a powerful new approach for understanding the similarities and differences between representations derived from behavior and CNNs.

×
×

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.

×