NazirNayal8/RbA

Official code for RbA: Segmenting Unknown Regions Rejected by All (ICCV 2023)

40
/ 100
Emerging

This project helps computer vision engineers and researchers identify and segment 'unknown' or 'anomalous' regions within images, particularly in autonomous driving or surveillance contexts. It takes diverse image datasets as input and outputs precise segmentation masks that highlight unexpected objects or conditions. This tool is ideal for professionals building robust object detection and scene understanding systems.

No commits in the last 6 months.

Use this if you need to reliably detect and outline unusual or out-of-distribution elements in images that your standard object recognition models might miss.

Not ideal if you are looking for a pre-trained, off-the-shelf solution for common object detection tasks without the need for anomaly segmentation.

autonomous-driving image-segmentation anomaly-detection computer-vision robotics
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

71

Forks

11

Language

Python

License

MIT

Last pushed

Jan 10, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/NazirNayal8/RbA"

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