What is ViT vs CNN? Why does it exist? Where does it appear in Vision Transformers (ViT)?
Draw or describe a visual model of ViT vs CNN. What does it look like conceptually?
How is ViT vs CNN different from related concepts in Vision Transformers (ViT)? What are the trade-offs?
Explain ViT vs CNN in plain language using an analogy. Could a non-expert follow it?