Note: This question is part of a series of questions that present the same scenario. Each question in the series contains a unique solution that might meet the stated goals. Some question sets might…

Question

Options

• AYes
• BNo

• A
  8% (3)
• B
  93% (37)

Explanation

Why B is correct: Creating a brand-new model discards all previously learned knowledge - you'd be starting from scratch rather than building on the existing classifier. The correct approach is to add the new images and labels directly to the existing Custom Vision project, then retrain that same model so it learns the new species without forgetting the old ones.

Why A is wrong: Uploading images to a new model means the classifier loses all prior training data and learned patterns from the original flower species. This defeats the purpose of an incremental update and requires far more data and effort than necessary.

Memory tip: Think of a Custom Vision model like a student's notebook - you don't throw away the notebook and start over when you learn something new; you add new pages (images) to the same notebook (project) and review everything together (retrain). When exam questions say "add to" or "update," the answer almost always involves the existing resource, not a new one.

No community discussion yet for this question.