Courseiva

AI-900 Practice Question: Describe features of computer vision workloads on Azure

What is 'zero-shot object detection' in computer vision?

⚠ Common exam trap

Many candidates confuse the term 'zero-shot' with performance metrics like latency, image color depth, or accuracy, rather than understanding it as a training paradigm where the model generalizes to unseen classes via natural language descriptions.

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

Detecting objects described in text without any training examples of that specific class

Zero-shot object detection refers to a model's ability to detect objects in images based on a textual description of the target class, without having been trained on any labeled examples of that specific class. This is achieved by leveraging a joint embedding space where visual features and text features are aligned, allowing the model to generalize to unseen categories at inference time.

Answer analysis

Option-by-option breakdown

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

  • Object detection that runs with zero latency for real-time applications

    Why it's wrong here

    This option describes an engineering optimization target, not a learning paradigm. Latency depends on hardware, model architecture, quantization, and pruning, and it measures when results arrive, not what the model can understand. In zero-shot detection, the model computes similarity between image features and text embeddings to handle novel classes, a capability entirely independent of inference speed.

  • Detecting objects described in text without any training examples of that specific class

    Why this is correct

    Zero-shot object detection uses a vision-language embedding space in which image regions and text descriptions are projected into the same representational space. At inference, the model scores each region against the embedding of the provided text prompt and outputs bounding boxes for regions with high alignment. Because the target class is defined semantically by text rather than by labelled training images, the detector can find object categories that were never seen during training.

  • Detection that works on black and white images (zero colour channels)

    Why it's wrong here

    Grayscale input is an image-preprocessing or network-channel consideration; object detectors can be adapted to accept single-channel inputs without changing what 'zero-shot' means. The term zero-shot refers to zero labelled examples of the target class during training, not zero color channels. These are unrelated uses of 'zero', so this is not a valid definition of zero-shot object detection.

  • An object detection model with zero false positives on the test set

    Why it's wrong here

    This statement confuses an evaluation metric with a capability definition. Achieving zero false positives on a specific test set means the model had perfect precision on those particular images, but it says nothing about generalizing to unseen categories. Zero-shot object detection refers specifically to the ability to localize objects described in a text prompt without having been trained on labelled examples of that class.

About these practice questions

One of 985 original AI-900 practice questions on Courseiva, each with a full explanation and wrong-answer analysis — not exam dumps or protected exam content. Learn why practice questions differ from exam dumps →

How Courseiva writes practice questions · Editorial policy

JA

Written by Johnson Ajibi, MSc IT Security

Senior Network & Security Engineer · founder of Courseiva

This AI-900 practice question is part of Courseiva's free Microsoft certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the AI-900 exam.