AI-102 Implement computer vision solutions Practice Question
You work for a manufacturing company that uses Azure AI services to automate quality inspection on a production line. You have a Custom Vision object detection model that identifies defects on metal parts. The model was trained on images captured under ideal lighting conditions. However, when deployed in the factory, the model's accuracy drops significantly due to inconsistent lighting and glare. You need to improve the model's robustness without collecting new images from the factory floor. What should you do?
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
✓
Apply data augmentation techniques such as brightness, contrast, and blur adjustments to the existing training images.
Using data augmentation techniques like brightness and contrast adjustments, rotation, and noise injection can simulate various lighting conditions and improve robustness. Option A is wrong because increasing training iterations may overfit to the existing data. Option C is wrong because higher resolution does not address lighting variation. Option D is wrong because changing the model type does not address the data issue.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Increase the number of training iterations to force the model to learn more features.
Why it's wrong here
More training iterations cannot teach invariance to lighting and glare absent from the training images; the model simply overfits existing features. Iteration tuning suits convergence problems, not domain shift. The correct approach augments existing images with brightness, contrast and glare transformations to simulate factory conditions.
- ✓
Apply data augmentation techniques such as brightness, contrast, and blur adjustments to the existing training images.
Why this is correct
Augmentation synthesises lighting variation—brightness, contrast and blur—directly from the existing dataset, so the detector learns glare-invariant features without any new factory-floor capture. This satisfies the stem's constraint of improving robustness under inconsistent lighting while collecting no additional images.
- ✗
Use higher resolution images for training.
Why it's wrong here
Resolution alone cannot synthesise the glare and lighting variance the model never saw; Custom Vision learns pixel patterns, so upscaling ideal-light images adds detail without adding illumination diversity. It tempts because higher resolution genuinely helps detect small defects when training images are already representative of deployment conditions.
- ✗
Change the model type from object detection to classification.
Why it's wrong here
Classification returns one label per image and cannot localise defects, so it discards the bounding-box output the inspection line consumes. It tempts because classification needs less training data and is robust to background variation, making it correct when the task is only pass/fail per part, not defect location.
Go deeper
Related to this question
About these practice questions
This AI-102 question is part of Courseiva's 761-question bank — original exam-style content with full explanations and wrong-answer analysis, never real exam questions or exam dumps. Learn why practice questions differ from exam dumps →
JA
Written by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
This AI-102 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-102 exam.