Skip to main content

Mask R-CNN

What is Mask R-CNN​

Mask R-CNN is a Convolutional Neural Network (CNN) and state-of-the-art in terms of image segmentation. This variant of a Deep Neural Network detects objects in an image and generates a high-quality segmentation mask for each instance.

Here is one example of a pair of images and segmentation masks.

Untitled

Untitled

Example from TorchVision Object Detection Finetuning Tutorial from PyTorch

What is R-CNN​

The term R-CNN or RCNN, stands for Region-Based Convolutional Neural Network, it is a type of machine learning model that is used for computer vision tasks, specifically for object detection.

How to implement the Mask R-CNN in PyTorch​

Here are some resources about training Mask R-CNN in PyTorch.

Acknowledgement : The content of this document has been adapted from this original Mask R-CNN : A Beginner’s Guide.