Skip To Content

Introduction to the model

Banner image for the model

The Image Interrogation pretrained model available on ArcGIS Living Atlas of the World is a deep learning model that is used to classify images.

This deep learning package (DLPK) serves as a connection between ArcGIS Pro and vision language models, supporting OpenAI's GPT-4 and GPT-4o, as well as Llama models. OpenAI and Llama Vision models are known for their advanced capabilities in natural language processing and understanding, and interpreting and generating human-like text. These models are also designed for tasks such as visual recognition, image reasoning, captioning, and responding to general questions about images. The integration of these models into a DLPK enhances their utility by enabling them to process images and perform a variety of vision-based tasks, including classification, visual question answering, and image captioning.

Use this DLPK to use OpenAI's large vision language and Llama Vision models to perform interrogation on images and rasters in ArcGIS Pro. This DLPK allows for flexibility in performing visual questio n answering and image captioning. This analysis and interpretation of spatial data allows professionals in fields such as environmental science, urban planning, and remote sensing to extract meaningful insights from their visual datasets.

License requirements

To complete this workflow, the following are the license requirements:

  • ArcGIS DesktopArcGIS Image Analyst extension for ArcGIS Pro
  • ArcGIS EnterpriseArcGIS Image Server with raster analytics configured
  • ArcGIS OnlineArcGIS Pro or Professional Plus user type

Model details

This model has the following characteristics:

  • Input—8-bit RGB imagery.
  • Output—Feature class with information about the image.
  • Compute—This workflow can run on CPU or GPU.
  • Applicable geographies—This model is expected to work well globally.
  • Architecture—The implementation uses either OpenAI's vision language models or Llama Vision models.

Access and download the model

Download the Image Interrogation pretrained model from ArcGIS Living Atlas of the World. Alternatively, access the model directly from ArcGIS Pro, or use it in ArcGIS Image for ArcGIS Online.

To download the model, complete the following steps:

  1. Browse to ArcGIS Living Atlas of the World.
  2. Sign in with your ArcGIS Online credentials.
  3. Search for Image Interrogation and open the item page from the search results.
  4. Click the Download button to download the model.

    You can use the downloaded .dlpk file directly in ArcGIS Pro.

Release notes

The following are the release notes:

DateDescription

March 2025

First release of Image Interrogation