I want to do an instance segmentation of objects in images.
Usually I would stick to something like an Mask R CNN and let it run. However additionally to the image itself and the pre-labeled images, I have additional features that might be interesting for the segmentation.
Example: I want to segment certain products in images from a factory and I have additional information about the products than run at a specific time (like product family, color, brand, etc.).
How do I add these additional features in an instance segmentation?
Seems easier to just search for images based on the additional information and then train on those images. You would have to first predict the brand(which again requires you to extract visual features from product images of that brand) and maybe do ocr(slow) and use that to filter region proposal.