NoCohen66/Verification4ObjectDetection

🩺🛣️ IBP IoU an approach for the formal verificaion of object detection models.

20
/ 100
Experimental

When you're using AI models for object detection, especially in critical applications like autonomous vehicles or medical imaging, you need to be sure they're robust against minor changes to input images. This project helps evaluate how stable your object detection model is by checking if its bounding box predictions (Intersection over Union, or IoU) remain reliable even when the image has small distortions like brightness, contrast, or noise. This is for AI engineers or researchers who build and deploy object detection systems and need to formally verify their robustness.

No commits in the last 6 months.

Use this if you need to rigorously test how small changes to an image's brightness, contrast, or noise affect your object detection model's accuracy, specifically focusing on the Intersection over Union metric.

Not ideal if you are looking for a general-purpose object detection model or a tool for data labeling, rather than formal robustness verification.

AI model verification object detection robustness machine learning safety computer vision testing autonomous systems
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 4 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

8

Forks

Language

Jupyter Notebook

License

LGPL-3.0

Last pushed

Jun 07, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/NoCohen66/Verification4ObjectDetection"

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