Viet-Anh on Software Logo

What is: Non Maximum Suppression?

Year2000
Data SourceCC BY-SA - https://paperswithcode.com

Non Maximum Suppression is a computer vision method that selects a single entity out of many overlapping entities (for example bounding boxes in object detection). The criteria is usually discarding entities that are below a given probability bound. With remaining entities we repeatedly pick the entity with the highest probability, output that as the prediction, and discard any remaining box where a IoU0.5\text{IoU} \geq 0.5 with the box output in the previous step.

Image Credit: Martin Kersner