PROFESSIONAL-MACHINE-LEARNING-ENGINEER · Question #297
You work for a company that builds bridges for cities around the world. To track the progress of projects at construction sites, your company has set up cameras at each location. Each hour, the…
The correct answer is A. Train an AutoML object detection model to annotate the objects in the images to help specialists. To scale image review and reduce costs with minimal up-front cost for specialized construction equipment annotation, train an AutoML object detection model to assist specialists.
Question
Options
- ATrain an AutoML object detection model to annotate the objects in the images to help specialists
- BUse the Cloud Vision API to automatically annotate objects in the images to help specialists with
- CCreate a BigQuery ML classification model to classify important images. Use the model to predict
- DUse Vertex AI to train an open source object detection to annotate the objects in the images to
How the community answered
(40 responses)- A75% (30)
- B3% (1)
- C8% (3)
- D15% (6)
Why each option
To scale image review and reduce costs with minimal up-front cost for specialized construction equipment annotation, train an AutoML object detection model to assist specialists.
Training an AutoML object detection model is ideal for annotating specific, custom objects like specialized construction equipment. AutoML reduces the need for deep ML expertise (minimal up-front cost for development) while providing a managed service that scales and helps automate the annotation process, significantly reducing manual effort and costs over time.
The Cloud Vision API is a pre-trained API that may not recognize 'unique specialized construction equipment' specific to the company's domain, requiring custom training which it doesn't support for new object types.
BigQuery ML classification is for tabular data or classifying entire images, not for detecting and annotating specific objects within images.
Training an open-source object detection model, while flexible, typically incurs higher up-front development and operational costs due to the need for ML expertise for model selection, tuning, and infrastructure management compared to AutoML.
Concept tested: Vertex AI AutoML object detection
Source: https://cloud.google.com/vertex-ai/docs/start/automl-image-object-detection
Topics
Community Discussion
No community discussion yet for this question.