Syllabus

Welcome to this Training Workshop on using BRAILS++. This year’s offering will be in an online format. A drawback of an online offering is the lack of interaction among the participants, so we encourage you to be active during the live sessions with questions.

Day 1: Image classification, detection, segmentation

• In-class presentations

  • Overview of Computer Vision Applications for Natural Hazards: Slides

  • Brief introduction to image classification, detection, segmentation: Slides

• Demo

  • Training a Building Damage Classifier Using BRAILS: Jupyter Notebook

Day 2: Vision foundation models

• In-class presentation

  • Vision Language Models: Slides

• Demos

  • Using CLIP for Zero-Shot Image Classification: Jupyter Notebook

  • Using CLIP for Zero-Shot Image Classification: Jupyter Notebook

• Hands-on activity

  • Distilling a segmentation model from GroundedSAM: Jupyter Notebook

Day 3: Using BRAILS for inventory generation and damage detection

• In-class presentation

  • Using BRAILS for inventory generation and damage detection: Slides

Warning

To run the demo on Day 3, you need to get a Google Maps API key before the class. To generate your API key:

1. Please visit this page,

2. Follow the instructions under “Using API Keys”.