Grounding DINO vs. OWL ViT: Compared and Contrasted

Models

Learn more about

OWL ViT

OWL-ViT is a transformer-based object detection model developed by Google Research.

Learn more about OWL ViT

Model Type

Object Detection

Model Features

Item 1 Info

Item 2 Info

Architecture

Frameworks

Annotation Format

Instance Segmentation

GitHub

View Repo

GitHub Stars

License

Paper

View Paper

Training Notebook

Train on Colab

Deploy Model

Deploy with Roboflow

Compare Alternatives

Compare and OWL ViT with Autodistill

Using Autodistill, you can compare Grounding DINO and OWLViT on your own images in a few lines of code.

Here is an example comparison:

To start a comparison, first install the required dependencies:


pip install autodistill autodistill-grounding-dino autodistill-owl-vit

Next, create a new Python file and add the following code:


from autodistill_grounding_dino import GroundingDINO
from autodistill_owl_vit import OWLViT

from autodistill.detection import CaptionOntology
from autodistill.utils import compare

ontology = CaptionOntology(
    {
        "solar panel": "solar panel",
    }
)

models = [
    GroundingDINO(ontology=ontology),
    OWLViT(ontology=ontology)
]

images = [
    "/home/user/autodistill/solarpanel1.jpg",
    "/home/user/autodistill/solarpanel2.jpg"
]

compare(
    models=models,
    images=images
)

Above, replace the images in the `images` directory with the images you want to use.

The images must be absolute paths.

Then, run the script.

You should see a model comparison like this:

When you have chosen a model that works best for your use case, you can auto label a folder of images using the following code:


base_model.label(
  input_folder="./images",
  output_folder="./dataset",
  extension=".jpg"
)

‍

Grounding DINO vs. OWL ViT

Models

OWL ViT

Compare and OWL ViT with Autodistill

Compare Grounding DINO vs. OWL ViT