This class was learned from 59 images of Cork. The visualizations below show the maximally activated representations of what makes Cork look like Cork. 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.
- Images used for training: 59
- Image sources: Google (39) , Flickr (14)
- Bounding boxes and URLs: wine-cork.json