OWL-V2

OWL-V2: Optimized for Qualcomm Devices

OWL-V2 (Open-World Localization with Vision Transformers) is an open-vocabulary object detector that uses a CLIP-based ViT-B/16 backbone. Given an image and one or more free-form text queries, the model predicts bounding boxes and confidence scores for each query.

This is based on the implementation of OWL-V2 found here. This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the Qualcomm® AI Hub Models library to export with custom configurations. More details on model performance across various devices, can be found here.

Qualcomm AI Hub Models uses Qualcomm AI Hub Workbench to compile, profile, and evaluate this model. Sign up to run these models on a hosted Qualcomm® device.

Getting Started

There are two ways to deploy this model on your device:

Option 1: Download Pre-Exported Models

Below are pre-exported model assets ready for deployment.

For more device-specific assets and performance metrics, visit OWL-V2 on Qualcomm® AI Hub.

Option 2: Export with Custom Configurations

Use the Qualcomm® AI Hub Models Python library to compile and export the model with your own:

• Custom weights (e.g., fine-tuned checkpoints)
• Custom input shapes
• Target device and runtime configurations

This option is ideal if you need to customize the model beyond the default configuration provided here.

See our repository for OWL-V2 on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.object_detection

Model Stats:

• Input image resolution: 960x960
• Model checkpoint: google/owlv2-base-patch16-ensemble
• Model size (float): 620 MB
• Number of parameters: 155M

Performance Summary

License

• The license for the original implementation of OWL-V2 can be found here.

References

• Scaling Open-Vocabulary Object Detection
• Source Model Implementation

Community

• Join our AI Hub Slack community to collaborate, post questions and learn more about on-device AI.
• For questions or feedback please reach out to us.