Auto Label
Auto-label images for use in training models.
Auto Label is one of many AI Labeling features. Using this feature will consume credits at the rates listed on our credits page.
Roboflow Auto Label lets you use large foundation vision models (i.e. Grounding DINO), Roboflow trained models, or a saved Workflow to automatically label images.
Roboflow Auto Label can use the following sources to identify the objects you specify:
Grounding DINO (Object detection)
Grounded SAM (Segmentation)
CLIP (Single- and multi-label classification)
Models trained in Roboflow (Train a Model)
Note: Only models from the same dataset as your Annotation Batch are currently supported.
A saved Workflow compatible with your project type
Auto Label is powered by Autodistill, an open source framework for auto-labeling image datasets developed by Roboflow.
Auto Label has been used to label millions of images for use in training computer vision models.
When to Use Roboflow Auto Label
You should use Roboflow Auto Label if you need to annotate common objects such as vehicles (i.e. forklifts), people, generic defects (i.e. cracks), and generic products (i.e. vinyl records, bread).
You should not use foundation models in Autodistill if you need to identify specific variants of an object. For example, Autodistill cannot distinguish between different types of crack, or identify unique defects in electronics.
Label Data with Roboflow Auto Label
The Roboflow platform lets you preview how Autodistill will perform on labeling classes of data in your dataset. Then, Roboflow will share a code snippet that you can use to auto-label images on your own hardware. You can upload your labeled dataset back to Roboflow for quality assurance (recommended) and to train a model.
Step #1: Upload Data
First, upload data to Roboflow. See our Upload Images, Videos, and Annotations instructions for more information.
Step #2: Enter Auto Label
Once you have uploaded all of your images, you will be asked how you want to label your images. Select "Auto Label".
Step #3: Configure Auto Label
The Auto Label labeling interface will appear in which you can configure your auto labeling job.
Classes (& Descriptions)
Classes represent the labels you want to assign to objects in the image. Descriptions represent a visual description of the class that your chosen foundation model (Grounding DINO by default) will use to identify instances of those classes. By default, the description will be the class name.
Auto Label works best when labeling common objects with clear visual descriptions. For example, Auto Label will be able to identify the location of an aluminum can on a production line. But, Auto Label will be unable to label images according to specific requirements, such as distinguishing the brand of an aluminum can.
Generating Test Results
Once you have configured Auto Label, click "Generate Test Results" to test your classes on a small subset of your dataset. By default, four images are selected.
Step #4: Evaluate Roboflow Auto Label Labels
Here are the test results when using the class "aluminum can" on an example image. From here, you can:
Adjust your classes & descriptions
If Auto Label doesn't label images as expected, try testing different descriptions for your classes.
All test results are free & don't use any credits.
Adjust the confidence
The number to the right of each class is represented as (boxes of this class that are shown) / (total boxes of this class). You can adjust the confidence threshold of each class to filter out more or less boxes. Higher confidence means less boxes will be shown.
The confidence threshold set here will be the same one used when labeling the entire batch, so make sure it looks right!
Test on different images
To review Auto Label's performance on different images from your batch, click on an image in the "Test images" section on the bottom left. The preview for that image should load immediately without pressing additional buttons.
Label with a Workflow
Instead of a foundation or trained model, you can auto-label with a saved Workflow, letting you use SAHI, model ensembles, and multi-step custom logic to label your batch.
In the Auto Label model dropdown, open the "Workflows" tab and select a workflow. Only workflows compatible with your project type (detection, segmentation, or classification) are listed.
After selecting a workflow, map each of its output classes to a class in your project and set a per-class confidence threshold. A preview runs on sample images so you can confirm the mapping before starting the job.
Only the classes you map are applied. Output classes with no mapping are dropped, so map every class you want written back to your project.
When the mapping looks right, start the job. It runs in the background and applies the mapped labels to your batch.
Run Auto Label On Your Batch
If Auto Label labels your images as you expect, click "Auto Label with This Model". Review the summary modal, and click to proceed. It should take a few minutes to label a thousand images.
Once the job starts, you are taken to the Annotate page, where the new Auto Label job is listed alongside your other annotation jobs. Auto Label runs in the background, so you can review results there when it finishes.
Last updated
Was this helpful?