A map-archive wants the same transformer family that reads catalog sentences to also read a sheet by cutting it into patches. What architecture idea is that?
Select an answer to reveal the explanation.
Short Explanation
Slice the map into postage-stamp tiles and hand the stack to the same kind of reader that already handles word tokens. Image-as-tokens lets a transformer serve as a vision encoder. It is not a third-party model catalog quiz.
Full Explanation
Vision transformers divide an image into patches, embed those patches as tokens, and process the sequence with transformer blocks. That image-as-tokens design reuses the transformer family as a vision encoder. Associate depth explains the tokenization idea without naming an outside catalog.