Generative Vision Interview Questions #10 - The Receptive Field Illusion

Why stacking convolutions to build global context quietly turns distant features into mush, and how trading inductive bias for self-attention secures true edge-to-edge coherence.

You’re in a Senior ML Engineer interview at Midjourney and the interviewer asks:

“Your teammate wants to ship a U-Net for your new high-res image model because ‘convolutions capture both local and global features.’ You disagree. Defend it.”

Don’t say: “Transformers are just better, everyone uses DiT now.”

Too lazy. They just failed the question.

Here’s the…