Are Convolutional Neural Networks or Transformers more like human vision?

Shikhar Tuli, Ishita Dasgupta, Erin Grant, Thomas L. Griffiths

Research output: Contribution to conferencePaperpeer-review

20 Scopus citations

Abstract

Modern machine learning models for computer vision exceed humans in accuracy on specific visual recognition tasks, notably on datasets like ImageNet. However, high accuracy can be achieved in many ways. The particular decision function found by a machine learning system is determined not only by the data to which the system is exposed, but also the inductive biases of the model, which are typically harder to characterize. In this work, we follow a recent trend of in-depth behavioral analyses of neural network models that go beyond accuracy as an evaluation metric by looking at patterns of errors. Our focus is on comparing a suite of standard Convolutional Neural Networks (CNNs) and a recently-proposed attention-based network, the Vision Transformer (ViT), which relaxes the translation-invariance constraint of CNNs and therefore represents a model with a weaker set of inductive biases. Attention-based networks have previously been shown to achieve higher accuracy than CNNs on vision tasks, and we demonstrate, using new metrics for examining error consistency with more granularity, that their errors are also more consistent with those of humans. These results have implications both for building more human-like vision models, as well as for understanding visual object recognition in humans.

Original languageEnglish (US)
Pages1844-1850
Number of pages7
StatePublished - 2021
Event43rd Annual Meeting of the Cognitive Science Society: Comparative Cognition: Animal Minds, CogSci 2021 - Virtual, Online, Austria
Duration: Jul 26 2021Jul 29 2021

Conference

Conference43rd Annual Meeting of the Cognitive Science Society: Comparative Cognition: Animal Minds, CogSci 2021
Country/TerritoryAustria
CityVirtual, Online
Period7/26/217/29/21

All Science Journal Classification (ASJC) codes

  • Cognitive Neuroscience
  • Artificial Intelligence
  • Computer Science Applications
  • Human-Computer Interaction

Fingerprint

Dive into the research topics of 'Are Convolutional Neural Networks or Transformers more like human vision?'. Together they form a unique fingerprint.

Cite this