rohit901/cooperative-foundational-models

[WACV 2025] Official code for our paper "Enhancing Novel Object Detection via Cooperative Foundational Models"

39
/ 100
Emerging

This project helps computer vision practitioners accurately identify both familiar and entirely new types of objects within images. You input images, and it outputs bounding boxes and labels for all detected objects, including those it hasn't been specifically trained on. This is for researchers and developers building advanced computer vision systems for tasks like autonomous inspection or content moderation where encountering unexpected items is common.

Use this if you need to detect a wide variety of objects in images, including novel or previously unseen categories, without needing to retrain your entire system for every new object.

Not ideal if you only need to detect a fixed, predefined set of common objects and do not anticipate encountering any new categories.

object-detection computer-vision image-analysis open-set-recognition AI-research
No Package No Dependents
Maintenance 6 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 8 / 25

How are scores calculated?

Stars

84

Forks

5

Language

Python

License

MIT

Last pushed

Jan 02, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/rohit901/cooperative-foundational-models"

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