Skip to course content
Free computer vision course

Computer Vision and Multimodal AI

Module 08 Knowledge Check

5 questions. Pass mark 4 out of 5. Answer every question before checking the answer key below, then retry after reading the feedback.

1. Passing xywh boxes to code expecting xyxy…

2. The IoU threshold that counts as a detection is…

3. Without non-maximum suppression, a detector…

4. Lowering the confidence threshold…

5. A 30x12 pixel barcode in a 1920px image, resized to 224px, becomes…

---

Answer Key and Explanations

Check these only after attempting every question.

1. B - produces boxes in the wrong place with no error

Every format is four numbers, so a mismatch is silent. Convert at the boundary and assert.

2. B - a choice that changes every reported number

mAP at 0.5 and at 0.5:0.95 are different numbers for the same model.

3. B - reports one object as several

Every count and every precision figure derived from the count is then wrong.

4. B - raises recall and lowers precision

This is mechanical and holds for every detector; which end you want follows from error costs.

5. B - under 4x2 pixels - destroyed before the model sees it

The remedy is tiling at native resolution, not a larger backbone.

Practical Check

Apply this module to your own work: complete the module activity for *Object Detection Concepts and Bounding Boxes*, then write one sentence naming what your result shows and one naming what it does not.

Strong Answer Pattern

A strong answer names the task, the evidence used, the check performed, and the remaining limitation. It avoids "proved", "guaranteed", or "always" unless the evidence genuinely supports it.