Models

OWL ViT vs. DETIC

Both

OWL ViT

and

DETIC

are commonly used in computer vision projects. Below, we compare and contrast

OWL ViT

and

DETIC

.

  OWL ViT DETIC
Date of Release Jan 07, 2022
Model Type Object Detection Instance Segmentation
Architecture
GitHub Stars 1400

Compare OWL ViT and DETIC with Autodistill

Using Autodistill, you can compare OWL ViT and DETIC 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-owl-vit autodistill-detic

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


from autodistill_owl_vit import OWLViT
from autodistill_detic import DETIC

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

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

models = [
    OWLViT(ontology=ontology),
    DETIC(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"
)

OWL ViT

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

How to AugmentHow to LabelHow to Plot PredictionsHow to Filter PredictionsHow to Create a Confusion Matrix

DETIC

Detic is an open source segmentation model developed by Meta Research and released in 2022.

How to AugmentHow to LabelHow to Plot PredictionsHow to Filter PredictionsHow to Create a Confusion Matrix

Compare OWL ViT to other models

Compare DETIC to other models

Deploy a computer vision model today

Join 250,000 developers curating high quality datasets and deploying better models with Roboflow.

Get started