Project AURIONAI Use-Cases Research & Innovation
visionfamily

OWL-ViT

Google open-vocabulary object detectors built on CLIP-style vision transformers, prompted by text or an example image.

GoogleGoogleUSA
Google
Levelfamily
Classvision
Parametersnot in the notes
Contextnot in the notes
Released12 May 2022
Opennessopen source
Runs onmobile or NPU
Statusactive

Lineage

202220232024OWL-ViT B/32OWL-ViT B/32, May 2022OWLv2 B/16 ensembleOWLv2 B/16 ensemble, Jun 2023OWLv2 L/14, Jun 2023
GoogleOWLv2 B/16 ensemble belongs to this familyvision16 Jun 2023154.97M
GoogleOWLv2 L/14 belongs to this familyvision16 Jun 2023437.61M
GoogleOWL-ViT B/32 belongs to this familyvision12 May 2022153.23M
Where this comes from
Parent and child relations from model cards, Hugging Face base_model fields and the genealogy tables of the research notes. Confidence and evidence are the notes' own.

R&D Topics

Open-vocabulary object detection and groundingproduced by

Identity

Developer
Google
Family
not in the notes
Released
12 May 2022 sourcesannouncement page
Weights published
–
Record checked
12 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.

Architecture and Size

Architecture
dense transformer
Total parameters
– sources
Active parameters
–
Checkpoint parameters
–
Note
OWL-ViT B/32, B/16, L/14; OWLv2 base and large (ensemble and fine-tuned).
Context length
not in the notes
Input
image, text
Output
labels and boxes
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).

Openness and Access

Openness
open source
Licence
Apache License 2.0 sources
Access routes
open weights download, cloud marketplace
Where this comes from
The licence file governs over registry tags and aggregator labels.

Deployment

Runs on
mobile or NPU
Footprint
Edge or toolkit builds listed in: Qualcomm AI Hub.
Runtimes
not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.

Indonesia

Indonesian support
not stated
Regional languages
not in the notes
Jakarta hosting
unknown
Languages
not in the notes
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.

Benchmark Results

The notes record no benchmark result for this model.

Industry Use Cases

No industry use case links this model.

Sources

  1. arxiv.org/abs/2205.06230 https://arxiv.org/abs/2205.06230
  2. github.com/google-research/scenic https://github.com/google-research/scenic
  3. github.com/GoogleCloudPlatform/vertex-ai-samples/tree/ma... https://github.com/GoogleCloudPlatform/vertex-ai-samples/tree/main/notebooks/community/model_garden
  4. huggingface.co/google/owlv2-base-patch16-ensemble https://huggingface.co/google/owlv2-base-patch16-ensemble
  5. huggingface.co/google/owlvit-base-patch32 https://huggingface.co/google/owlvit-base-patch32
  6. aihub.qualcomm.com/models/owl_vit https://aihub.qualcomm.com/models/owl_vit
  7. github.com/google-research/scenic/tree/main/scenic/proje... https://github.com/google-research/scenic/tree/main/scenic/projects/owl_vit

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "OWL-ViT", https://aurion.semai.id/models/google-owl-vit/, records of October 2026.