scuwyh2000/RandBox

[ICCV 2023] PyTorch implementation of RandBox

25
/ 100
Experimental

This project helps computer vision practitioners detect a wide range of objects in images, even those it hasn't been explicitly trained on. You input images, and it outputs bounding box detections and labels for both known and previously unseen objects. This is ideal for vision engineers or AI researchers building robust object detection systems.

No commits in the last 6 months.

Use this if you need an object detection system that can identify new, unexpected objects in an image without needing to be retrained on them.

Not ideal if you only need to detect a fixed set of known objects and prefer a simpler, potentially faster, closed-set detector.

computer-vision object-detection open-world-recognition image-analysis
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 9 / 25

How are scores calculated?

Stars

56

Forks

5

Language

Python

License

Last pushed

Nov 04, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/scuwyh2000/RandBox"

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