DESIGN DIFFERENCE CAPTIONING ON PRODUCTIVITY APPLICATIONS FOR LOW VISION USERS

A computing device may receive a plurality of sample slides with various layouts, receive a plurality of augmentations, select one or more augmentations from the plurality of augmentations that are compatible with each other, apply the selected augmentations to the plurality of sample slides to create a plurality of perturbed slides, generate a plurality of slide pairs by combining the plurality of sample slides and the plurality of perturbed slides, filter one or more slide pairs of the plurality of slide pairs that are visually the same, generate the synthetic design dataset including the filtered slide pairs and one or more classes of perturbation that are associated with each of the filtered slide pairs, and train a predictive model using synthetic design dataset for predicting one or more predicted augmentations indicative of one or more layout differences between a pair of slides.