Is there a way to set different confidence thresholds for different classes using Detectron2?
I am working on an object detection model for microscopic images. Some of my classes are very simple (feature wise), they are practically fancy lines. Some are more complicated objects. My problem is that I am getting a lot of False Positives for the simple classes, because anything that looks loke a line gets classified.
I am using the Detectron2 framework and I wonder if there is a way to set a higher confidence threshold for the simple classes?
Topic object-detection deep-learning
Category Data Science