This class was learned from images of . The visualizations below show the maximally activated representations of what makes look like . Each image begins with a randomly-seeded noise image, which leads to a slightly different class representation. Below are 12 activations created from 12 random noise images.

Data Sources
  • Images used for training:
  • Image sources: Google () , Flickr ()
  • Bounding boxes and URLs: comte-cheese.json