Open-vocabulary detection by adding one trained projection to a closed-set RF-DETR Small detector, served by VisionServe The detector exports the 256-d feature fi of each of its 300 object queries as an extra ONNX output, queryfeats. A trained matrix P maps that feature into the text-embedding space of a CLIP or SigLIP text tower, and each class gets a cosine score against the embedding of its name: The vocabulary is the prompt, for example "cup. cola can. banana.". Changing it needs no re-export and no second detector: the text tower runs once per new vocabulary, and the result is cached. Boxes always come from the detector. pull downloads one subfolder of this repo, writes a…
Independent publisher
Trung M. Bui
mtbui2010
Models in Library1
Datasets in Library0
Models on Hugging Face5
Followers—
Compare the published evidence
This profile connects the 1 model and dataset record shown below to their upstream cards and sources. The library counts describe SAVRN's coverage, rather than this publisher's entire output.
Published tasks: Zero shot object detection.
Reported licenses: apache-2.0. Open a record to review its specific license and conditions.
Compare model specifications, source dates, and hardware estimates on the individual records. Publisher identity verification is separate from a model's quality, deployment readiness, or suitability for your work.