This class was learned from 123 images of Croissant. The visualizations below show the maximally activated representations of what makes Croissant look like Croissant. 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: 123
- Image sources: Google (70) , Flickr (45)
- Bounding boxes and URLs: croissant.json