2

A bounding box is a rectangle superimposed over an image within which all important features of a particular object is expected to reside. It's purpose is to reduce the range of search for those object features and thereby conserve computing resources: Allocation of memory, processors, cores, processing time, some other resource, or a combination of them. ...


2

My assumption was correct: the ground truth bounding box is aligned with an anchor box such that they share the same center In other words, only the widths and heights are used to calculate the ground truth IOU.


1

Yes, theoretically it is possible to learn the offsets to get any possible bounding box from only one anchor box. However, it is hard to learn such dramatic shifts and changes. Learning only small offsets from the prior is easier and tends to converge better. In specific applications however, one might already know the typical size and ratio of objects, and ...


1

There are some special architectures of CNNs which are designed exactly for the task you mention. The Detector library includes a collection of these architectures, this paper describes the Mask R-CNN network in detail, which is designed for image segmentation tasks.


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