mediumMultiple Choice
PMLE Practice Question: A company uses Vertex AI AutoML to train a vision…
A company uses Vertex AI AutoML to train a vision model, but the model has low accuracy. What should they do first?
⚠ Common exam trap
Google Cloud often tests the misconception that AutoML models are 'black boxes' where tuning budgets or switching to custom models is the first fix, when in reality the platform is optimized to handle those aspects automatically, and the primary lever is data quality.
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
✓
Add more labeled images to the dataset
Adding more labeled images directly addresses the most common cause of low accuracy in AutoML vision models: insufficient or unrepresentative training data. Vertex AI AutoML relies on transfer learning from pre-trained models, and its performance is heavily dependent on the quality and quantity of labeled examples. Before adjusting hyperparameters or infrastructure, the first step should always be to improve the dataset, as AutoML is designed to handle model architecture and training budget automatically.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
Add more labeled images to the dataset
Why this is correct
Low accuracy usually stems from insufficient or unrepresentative training data, so adding more labelled images addresses the root cause first. This satisfies the scenario's need to improve the dataset before tuning hyperparameters or changing model architecture.
- ✗
Switch to a custom model
Why it's wrong here
AutoML already handles model architecture and hyperparameter tuning, so switching to a custom model skips the diagnostic step of checking data quality, label accuracy and class balance, which typically cause low vision accuracy. Custom training is warranted only when AutoML's supported task types or latency constraints genuinely cannot meet requirements.
- ✗
Increase the training budget
Why it's wrong here
A larger training budget cannot fix low accuracy caused by mislabelled images, insufficient or unrepresentative data, or an unsuitable prediction type; AutoML already tunes hyperparameters within budget. Increasing budget is the right move only when diagnostics show the model is underfitting despite clean, sufficient, well-balanced training data.
- ✗
Reduce image size to speed up training
Why it's wrong here
Reducing image size discards pixel detail the vision model needs, lowering accuracy further rather than addressing the cause. It is tempting because smaller images train faster and cut cost, and would be correct when training time or cost, not accuracy, is the binding constraint.
Go deeper
Related to this question
About these practice questions
One of 775 original PMLE 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 →
JA
Written by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
This PMLE practice question is part of Courseiva's free Google Cloud 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 PMLE exam.