This class was learned from 157 images of Köttbullar. The visualizations below show the maximally activated representations of what makes Köttbullar look like Köttbullar. 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: 157
- Image sources: Google (92) , Flickr (64)
- Bounding boxes and URLs: kottbullar.json