Skip to course content
Free computer vision course

Computer Vision and Multimodal AI

Module 09 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. An individual dimension of an image embedding…

2. Two photos matching with high similarity may have matched on…

3. A similarity search for an object absent from the index…

4. Near-duplicates should be detected…

5. Searching an index with a different embedding model than built it…

---

Answer Key and Explanations

Check these only after attempting every question.

1. B - means nothing on its own

Only angles between vectors carry meaning, which is why every use is a comparison.

2. B - lighting, background or pose rather than the object

A general-purpose embedding cannot tell you which attribute drove a given match.

3. B - returns k results anyway, all irrelevant

A score threshold is what turns a ranking into a decision about whether to answer.

4. B - before splitting, by embedding similarity

File hashes miss video frames and burst photos, and a straddling pair inflates every score you report.

5. B - returns plausible, meaningless rankings

The vectors occupy different spaces. There is no symptom - record which model produced an index.

Practical Check

Apply this module to your own work: complete the module activity for *Embeddings and Image Similarity*, 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.