Implement computer vision solutions →hardMultiple Choice

AI-102 Implement computer vision solutions Practice Question

Exhibit

Refer to the exhibit.

```json
{
  "name": "MyCustomVisionProject",
  "description": "Project for logo detection",
  "domainId": "0732100f-1a38-4e49-a514-c9b44d6978f0",
  "classificationType": "Multilabel",
  "targetExportPlatforms": ["DockerFile", "TensorFlow"]
}
```

You are creating a new Custom Vision project with the above JSON. The domainId corresponds to the 'Logo' domain. Which type of model will this project train?

⚠ Common exam trap

Many candidates confuse the 'Logo' domain with object detection, assuming it draws bounding boxes around logos, when in fact it performs multilabel classification without localization.

Answer choices

Why each option matters

Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.

Correct answer & explanation

✓

A multilabel image classification model for logo detection

The 'Logo' domain in Custom Vision is specifically designed for image classification tasks, not object detection. When you create a project with the 'Logo' domain, it trains a multilabel image classification model, meaning each image can be assigned multiple labels (e.g., multiple logos in one image). This domain is optimized for identifying and classifying logos within images, making it distinct from object detection or general classification.

Answer analysis

Option-by-option breakdown

For each option: why learners choose it and why it is or isn't the right answer here.

✗
An object detection model for logo detection
Why it's wrong here
The Logo domain supports classification only; object detection requires the separate Logo (compact) or General domain with detection export. It is tempting because locating logos within images sounds like detection, but that capability is not offered by this domain, so bounding-box output is unavailable.
✗
An optical character recognition model
Why it's wrong here
The Logo domain trains image classification models, not OCR; OCR is a separate domain for reading text within images. It is tempting because logo images often contain text, but recognising characters is a distinct capability, and OCR would be correct only when extracting printed or handwritten text.
✓
A multilabel image classification model for logo detection
Why this is correct
The Logo domain is a multilabel classification domain, meaning each image can be assigned multiple logo tags simultaneously rather than one exclusive label. Training with that domainId therefore produces a multilabel image classification model for logo detection.
✗
A general image classification model
Why it's wrong here
The Logo domain is a specialised classification domain tuned for brand and logo recognition, not the general-purpose one. It is tempting because both produce classification models, but the general domain is correct when classifying arbitrary everyday image categories rather than logos.

Go deeper

AI-102 Implement computer vision solutions Practice Question

Exhibit

Why each option matters

Option-by-option breakdown

Related to this question