Skip to main content
2 votes

How does Mask R-CNN automatically output a different number of objects on the image?

Object detection models usually generate multiple detections per object. Duplicates are removed in a post-processing step called Non-Maximum Suppression (NMS). The ...
Kostya's user avatar
  • 2,534
1 vote

possible to combine multiple labeled objects as one object?

There are probably many ways to combine classes. Here is my suggestion: Figure out the mask pixel values for each of the classes you want to pool (e.g. ...
Snehal Patel's user avatar
1 vote

Why instance segmentation architectures using reconstruction masks but not regression?

The reason is probably that the segmentation polygons have various shapes and complexities. You don't know how many points you need per polygon so defining a proper output that specifies the polygons ...
Chillston's user avatar
  • 1,748
1 vote

Is Mask R-CNN suited to solve a multi-class classification problem where the classes are related?

Mask RCNN can be a very heavy function for a simple class classification. It is designed to handle multiple object in a single image. So I would suggest you could use much simpler models like VGGnet ...
Jayanthan Ramesh Vellore's user avatar

Only top scored, non community-wiki answers of a minimum length are eligible