The mask rcnn model is closely connected to. In the following weeks (or months) i am going to take a deep dive into deep learning based object detection models My goal is to create a series of posts regarding different approaches and popular architectures for this task. The model generates bounding boxes and segmentation masks for each instance of an object in the image It's based on feature pyramid network (fpn) and a resnet101 backbone After the region proposals are processed through roi align, the features are fed into the mask branch
The mask branch uses a convolutional neural network to predict a binary mask for each object in the proposal, indicating which pixels belong to the object and which do not. Learn about its architecture, functionality, and diverse applications.
OPEN
