Minimal Cost ML Solution for Image Annotation

PMLE By islever Editorial Last updated Aug 31, 2026

Short answer

A Train an AutoML object detection model to annotate the objects in the images to help specialists with the annotation task.

Question

You work for a company that builds bridges for cities around the world. To track the progress of projects at the construction sites, your company has set up cameras at each location. Each hour, the cameras take a picture that is sent to a Cloud Storage bucket. A team of specialists reviews the images, filters important ones, and then annotates specific objects in them. You want to propose using an ML solution that will help the company scale and reduce costs. You need the solution to have minimal up-front cost. What method should you propose?

Train an AutoML object detection model to annotate the objects in the images to help specialists with the annotation task. Correct Answer
Use the Cloud Vision API to automatically annotate objects in the images to help specialists with the annotation task.
Create a BigQuery ML classification model to classify important images. Use the model to predict which new images are important to help specialists with the filtering task.
Use Vertex AI to train an open source object detection to annotate the objects in the images to help specialists with the annotation task.

Key Takeaways

The question tests the ability to select a no-training-required solution (Cloud Vision API) versus a custom solution (AutoML) when the constraint is strictly minimal up-front cost.

To minimize up-front costs for image annotation, using pre-trained APIs like Cloud Vision API is preferred over training custom models like AutoML, which requires labeled data and training compute.

Common mistake: Choosing AutoML (Option A) because it offers custom detection, ignoring the 'minimal up-front cost' constraint which requires avoiding training data preparation and model training fees.

Expert Analysis

Why the Answer Is Correct

Cloud Vision API is a pre-trained, serverless service that requires no model training or labeled dataset setup. Users pay only for API calls, satisfying the "minimal up-front cost" requirement perfectly. It can immediately assist specialists by providing general object labels, filtering out noise, or identifying standard construction elements without initial investment.

Why the Other Options Are Wrong

AutoML (Option A) and Vertex AI (Option D) require a labeled dataset and incur training costs (compute + human labeling), violating the minimal up-front cost constraint. BigQuery ML (Option C) is not optimized for image classification workflows compared to Vision AI services and also requires training costs.

Community Comment Notes

While some voters prefer A for custom labels, comments [1], [4], and [5] correctly identify that "no upfront cost" dictates the use of a pre-trained API. Comment [1] explicitly states AutoML requires training data and costs, whereas B does not.

Official Reference

These links open the official vendor documentation in a new tab.

Exam Strategy

Look for keywords like 'up-front cost,' 'training data,' or 'custom.' If the question asks for low upfront cost or rapid prototyping without existing labels, always choose Pre-trained APIs over AutoML or Custom Training.

Community Votes

62%

38%

62% of anonymous learners picked answer A. Votes are pick records left by other test-takers — they are not the verified answer.

Discussion 5 contributions

Compiled from public community threads and reader submissions, lightly edited for clarity. Handles and vote tallies are shown as recorded, and comments reflect the views of individual contributors.

From public community threads 5

Omi_04040 👍 2 Answered A

Since we have corpus of images and custom lables, 'Cloud Vision API' wont help, also its not advisable to use BigQuery ML classification for Image data Hence ans is A
AB_C 👍 2 Answered A

While the Vision API can detect objects, it might not be as accurate or specific as a custom-trained model for this particular use case (bridge construction).
thescientist 👍 2 Answered B

AutoML requires training data and incurs training costs - for no upfront cost: B
strafer 👍 1 Answered A

Cloud Vision API: Pay-as-you-go and Ready-to-use: The Cloud Vision API offers pre-trained models for object detection (and many other image analysis tasks). It's a pay-as-you-go service, meaning you only pay for the API calls you make. This translates to minimal up-front cost since there's no model training or infrastructure setup required on your end. You can immediately start using the API with your existing image data.
vladik820 👍 1 Answered B

Cloud Vision API - Pay-per-use based on the number of images processed. No training required – it's a pre-trained API.

Reader comments & corrections

No reader corrections yet — spotted an error or have a note? Share it below.

Practice All PMLE Questions

Access 65 questions with complete answers and detailed explanations.

View Full PMLE Practice Test →

← Back to PMLE Study Guide