Using cropped background images as background class


I’m currently working on a binary image classification problem using high resolution (up to 6000x4000 pixels) images with complex backgrounds, and CNN transfer learning.

In order to reduce Images size and complexity, I applied an offline crop to all images in a way that keeps the Region Of Interest (ROI) distinguishable. This resulted with three types of cropped images:

  1. images with background only,
  2. images with ROI only, and
  3. images with both ROI and background.

Only images of type 1 and 2 were used to train validate and test the CNN model.

I want to use the background-only images (type 1) as a background class in order to make my model fucus only on ROI and ignore backgrounds. How can I deal with the background class (number of images, loss function…) ?