YOLO | Image Classification

Overview

The YOLO | Image Classification plugin allows you to add classifiers to an image or to individual annotations.

In image classification mode

In tool classification mode

Plugin Functionality

The YOLO | Image Classification Plugin allows automatic classification of images using a pre-trained YOLO model. The plugin analyzes each image (or selected regions) and assigns one or more class labels along with confidence scores, enabling fast and scalable annotation of large image datasets.

If you are going to use the image classification mode of this plugin, ensure you have created at least one text classification class in your project.

If you are going to use the tool classification mode of this plugin, ensure you have created at least one Bounding Box labeling tool in your project and that you have created the objects you would like the plugin to classify in the image you will pass as input.

Supported Data Types

• Image

Supported Annotation Tools

• Bounding Box

• Text

Plugin Configuration

The Overwrite setting in model plugins controls whether existing annotations are replaced or kept. When enabled, the plugin replaces all existing annotations with new model predictions; when disabled, it simply adds the new results without deleting what’s already there.

The Class Mapping setting defines how the model’s predicted classes are linked to your project’s label schema. Follow these steps to prepare your class mapping.

1. In the "Class Mapping" field, open the left dropdown, and pick from one of the classes the plugin can detect.

2. Open the right dropdown, and pick from one of the tools you have created in your project.

3. Click on the "plus" button to finalize the pairing. Now the object class and your bounding box tool are linked. The plugin will use the selected bounding box tool to label the selected category.

4. Starting again from Step 1, link as many tools to categories as needed.

YOLO | Image Classification plugin integration to the workflow

You may vary a number of settings related to your export from the Config JSON field. Each option is detailed below:

{
  "num_top_classes": 5,
  "classify": "asset"
}

• "num_top_classes": Defines how many of the highest-confidence predicted classes should be returned for each asset.

  • Example:

    • "num_top_classes": 3

• "classify": Determines the scope of classification. In the "asset" mode, the plugin classifies the entire image as a single unit. In the "tools" mode, the plugin classifies regions or segments selected via annotation tools, allowing more granular labeling.

  • Options:

    • "asset"

    • "tools"

  • Example:

    • "classify": "asset"

Predicted Classes

The plugin classifies each image into one of the following classes:

10KB

imagenet_classes.txt

Open