Non-max suppression performance
The following is intended for informational purposes only, and may not be incorporated into any contract. No purchasing decisions should be made based on the following materials. Unity is not committing to deliver any functionality, features or code. The development, timing and release of all products, functionality and features are at the sole discretion of Unity, and are subject to change.
If you have accepted to use functional cookies and logged in using your Unity ID at the top right of the page, then sharing feedback is as simple as clicking a card below, selecting a topic’s importance, adding your point of view, and submitting. If you prefer not to accept functional cookies or log in, you will be prompted to enter an email address and validate it, so we know how to reach out when the topic evolves. For more information read the Feedback and privacy terms.
What? Non-max suppression (NMS) is a post-processing calculation useful for objection detection, as seen in models such as YOLO. It can eliminate duplicate/overlapping bounding boxes and select the most relevant ones, making the model more accurate. Our previous implementation was too slow and hampered the performance of object detection, whereas the new calculation is very fast.
Why? Object detection is a popular use case for AI in Unity and we want to ensure the models for this are performant.