Computer Vision Interview Questions, issue 19, Jan 20, 2026
The Fine-Grained Invariance Trap
Senior Computer Vision Engineer interview at Google DeepMind, and the interviewer asks:
“We need to classify 10,000 distinct car models (Make, Model, Year) for a demographics study. How do you build the model?”
Why Global Average Pooling silently destroys the only features that matter in fine-grained classification.
The full answer, with the mechanism and the arithmetic, is for paid subscribers on Substack.