This class was learned from 219 images of Vespa. The visualizations below show the maximally activated representations of what makes Vespa look like Vespa. 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: 219
- Image sources: Google (114) , Flickr (54)
- Bounding boxes and URLs: vespa.json