Exploring the Mask R-CNN architecture

The Mask R-CNN architecture helps identify/highlight the instances of objects of a given class within an image. This becomes especially handy when there are multiple objects of the same type present within the image. Furthermore, the term Mask represents the segmentation that’s done at the pixel level by Mask R-CNN.

The Mask R-CNN architecture is an extension of the Faster R-CNN network, which we learned about in the previous chapter. However, a few modifications have been made to the Mask R-CNN architecture, as follows:

• The RoI Pooling layer has been replaced with the RoI Align layer.
• A mask head has been included to predict a mask of objects in addition to the head, which already predicts the classes of objects and bounding-box correction in the final layer.
• A fully convolutional network (FCN) is leveraged for mask prediction.

Let’s have a quick look at the events that occur within Mask R-CNN...