Any help?
Each bounding box is tagged to one of three classes: fruit_healthy, fruit_brownspot and fruit_woodiness; I could say that the fourth one corresponds to the case where there are no fruits at all on the picture.
If you mean 4 classes for the detector, there are 3 classes + 1 class for background. This is a common technique for the object detection task.
Each bounding box is tagged to one of three classes: fruit_healthy, fruit_brownspot and fruit_woodiness; I could say that the fourth one corresponds to the case where there are no fruits at all on the picture.
If you mean 4 classes for the detector, there are 3 classes + 1 class for background. This is a common technique for the object detection task.