Issue 9, Jan 10, 2026
The Tiny Object Trap
Senior Computer Vision Engineer interview at Amazon Fulfillment Technologies & Robotics, and the interviewer asks:
βWe need to detect tiny, 3mm micro-fractures on a fast-moving assembly line. You suggested π ππ¬πππ« π-πππ over ππππ. Why does the πππ π’π¨π§ ππ«π¨π©π¨π¬ππ₯ ππππ°π¨π«π€ (πππ) specifically help with small objects, even though it kills our inference speed?β
Donβt say: βBecause two-stage detectors are generally more accurate than single-stage detectors.ββ
Why Faster R-CNN still beats YOLO when defects are smaller than your receptive field.
Share this trapShare on LinkedIn
The full answer, with the mechanism and the arithmetic, is for paid subscribers on Substack.