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)