shreydan/VLM-OD

experimental: finetune smolVLM on COCO (without any special tokens)

22
/ 100
Experimental

This experimental project helps researchers and machine learning practitioners explore how a small Vision-Language Model (VLM) can be adapted for object detection. It takes an image and aims to identify and locate specified objects within it. The primary users are those working on computer vision tasks who want to experiment with VLM capabilities for object identification.

No commits in the last 6 months.

Use this if you are a researcher or developer prototyping basic object detection from a small VLM and are comfortable with experimental results.

Not ideal if you need a production-ready, highly accurate object detection system, especially for small objects or detecting multiple instances of the same object.

computer-vision object-detection machine-learning-research vision-language-models
No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 5 / 25
Maturity 7 / 25
Community 8 / 25

How are scores calculated?

Stars

9

Forks

1

Language

Jupyter Notebook

License

Last pushed

May 19, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/shreydan/VLM-OD"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.