Mask R-CNN — Mask Region-based Convolutional Neural Network

Fact

A vision model for finding objects and outlining each one pixel by pixel.

In Plain Words

Mask R-CNN is like magic scissors for a photo. It does not just box the dog. It cuts around the ears and tail.

You meet it in photo cutouts and self-driving cars. Doctors use it in scans too. It can find shapes down to pixels.

Related Concepts

• Faster Region-based Convolutional Neural Network
• Object Detection
• Image Segmentation
• Convolutional Neural Network

Faster R-CNN
Mask R-CNN adds mask prediction on top of Faster R-CNN boxes.

Object Detection
Object Detection finds object positions. Mask R-CNN also draws the outlines.

Image Segmentation
Mask R-CNN is a classic way to split each object into pixels.

CNN
A CNN gives Mask R-CNN the image features it uses.