Question 338 of 1,020

What Is Ground Truth in Computer Vision?

This AI-900 practice question tests your understanding of describe features of computer vision workloads on azure. Read the scenario carefully and evaluate each option against the stated constraints before committing to an answer. After answering, compare your reasoning against the explanation and wrong-answer breakdown below. Once you have made your selection, read the full explanation to reinforce the concept and understand why each distractor is designed to mislead on exam day.

What is the purpose of image 'ground truth' in training computer vision models?

Quick Answer

The answer is verified, accurate labels or annotations for training images that the model learns to predict. This is correct because ground truth serves as the definitive benchmark during supervised learning, where the computer vision model compares its own predictions against these known correct outputs to adjust its internal parameters. On the Microsoft Azure AI Fundamentals AI-900 exam, this concept tests your understanding of how labeled datasets drive model training, often appearing in questions about image classification or object detection workflows. A common trap is confusing ground truth with the model’s initial predictions—remember that ground truth is the human-verified reality, not the model’s guess. For a memory tip, think of ground truth as the “answer key” for your training data: just as a student learns from a correct answer sheet, the model learns from these precise labels to make accurate predictions on new images.

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

The verified, accurate labels or annotations for training images that the model learns to predict

In computer vision, 'ground truth' refers to the verified, accurate labels or annotations for training images. The model uses these correct labels during supervised learning to learn the mapping from image features to outputs, enabling it to make accurate predictions on new, unseen data.

Key principle: Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option.

Answer analysis

Option-by-option breakdown

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

  • The physical location where training images were captured

    Why it's wrong here

    Image location/origin is metadata — ground truth is the accurate label/annotation for training.

  • The verified, accurate labels or annotations for training images that the model learns to predict

    Why this is correct

    Ground truth provides correct answers for training examples — the model's goal is to produce predictions matching the ground truth.

    Related concept

    Read the scenario before looking for a memorised answer.

  • The minimum image resolution required for accurate model training

    Why it's wrong here

    Image quality requirements are data specifications — ground truth is the label/annotation content.

  • The baseline accuracy of a computer vision model before fine-tuning

    Why it's wrong here

    Baseline performance is an evaluation metric — ground truth is the set of correct labels for training data.

Common exam traps

Common exam trap: answer the scenario, not the keyword

The trap here is confusing 'ground truth' with a physical or performance-related concept, when it strictly refers to the authoritative labels used to supervise model training.

Detailed technical explanation

How to think about this question

Ground truth annotations are typically created by human labelers or automated tools and stored in formats like COCO JSON or Pascal VOC XML. In Azure Custom Vision, ground truth is provided by uploading images with bounding boxes, tags, or polygons. The model's loss function (e.g., cross-entropy) directly compares its predictions against these ground truth labels to compute gradients for weight updates during training.

KKey Concepts to Remember

  • Read the scenario before looking for a memorised answer.
  • Find the constraint that changes the correct option.
  • Eliminate answers that are true in general but not in this case.

TExam Day Tips

  • Watch for words such as best, first, most likely and least administrative effort.
  • Review why wrong options are wrong, not only why the correct option is correct.

Key takeaway

Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option.

Real-world example

How this comes up in practice

An e-commerce site experiences heavy traffic on Black Friday and near-zero traffic during off-peak weeks. Rather than provisioning permanent large VMs, the team uses auto-scaling groups that add capacity automatically under load and reduce it overnight. Questions like this test whether you understand elasticity, availability zones, and cloud compute scaling patterns.

What to study next

Got this wrong? Here's your next step.

Identify which exam domain this question belongs to, review the core concept, then practise similar questions from the same domain.

Related practice questions

Related AI-900 practice-question pages

Use these pages to review the topic behind this question. This is how one missed question becomes focused revision.

Practice this exam

Start a free AI-900 practice session

Short sessions build daily habit. Longer sessions build exam-day stamina. Try a timed session to simulate real conditions.

FAQ

Questions learners often ask

What does this AI-900 question test?

Describe features of computer vision workloads on Azure — This question tests Describe features of computer vision workloads on Azure — Read the scenario before looking for a memorised answer..

What is the correct answer to this question?

The correct answer is: The verified, accurate labels or annotations for training images that the model learns to predict — In computer vision, 'ground truth' refers to the verified, accurate labels or annotations for training images. The model uses these correct labels during supervised learning to learn the mapping from image features to outputs, enabling it to make accurate predictions on new, unseen data.

What should I do if I get this AI-900 question wrong?

Identify which exam domain this question belongs to, review the core concept, then practise similar questions from the same domain.

What is the key concept behind this question?

Read the scenario before looking for a memorised answer.

About these practice questions

Courseiva creates original exam-style practice questions with explanations and wrong-answer analysis. It does not publish real exam questions, exam dumps, or protected exam content. Learn why practice questions differ from exam dumps →

How Courseiva writes practice questions · Editorial policy

Keep practising

More AI-900 practice questions

Last reviewed: Jun 11, 2026

Question Discussion

Share a tip, memory trick, or ask about the reasoning behind this question. Do not post real exam questions, leaked content, braindumps, or copyrighted exam material. Comments are moderated and may be removed without notice.

Loading comments…

Sign in to join the discussion.

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.