Open Access Te Herenga Waka-Victoria University of Wellington
Browse

Shared Visual Abstractions

conference contribution
posted on 2023-05-08, 21:25 authored by Tom WhiteTom White
This paper presents abstract art created by neural networks and broadly recognizable across various computer vision systems. The existence of abstract forms that trigger specific labels independent of neural architecture or training set suggests convolutional neural networks build shared visual representations for the categories they understand. Computer vision classifiers encountering these drawings often respond with strong responses for specific labels - in extreme cases stronger than all examples from the validation set. By surveying human subjects we confirm that these abstract artworks are also broadly recognizable by people, suggesting visual representations triggered by these drawings are shared across human and computer vision systems.

History

Preferred citation

White, T. (2019, November). Shared Visual Abstractions. In Shared Visual Representations in Human and Machine Intelligence (SVRHM), Vancouver, Canada. https://arxiv.org/abs/1912.04217

Conference name

Shared Visual Representations in Human and Machine Intelligence (SVRHM)

Conference start date

2019-12-13

Conference finish date

2019-12-13

Contribution type

Published Paper

Publication or Presentation Year

2019-11-19

Publication status

Published

Place of publication

Vancouver, Canada

Usage metrics

    Conference papers

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC