Predicting Visual Importance Across Graphic Design Types

Camilo Fosco, Vincent Casser, Amish Kumar Bedi, Peter O’Donovan, Aaron Hertzmann, Zoya Bylinskii

Abstract. This paper introduces a Unified Model of Saliency and Importance (UMSI), which learns to predict visual importance in input graphic designs, and saliency in natural images, along with a new dataset and applications. Previous methods for predicting saliency or visual importance are trained individually on specialized datasets, making them limited in application and leading to poor generalization on novel image classes, while requiring a user to know which model to apply to which input. UMSI is a deep learning-based model simultaneously trained on images from different design classes, including posters, infographics, mobile UIs, as well as natural images, and includes an automatic classification module to classify the input. This allows the model to work more effectively without requiring a user to label the input. We also introduce Imp1k, a new dataset of designs annotated with importance information. We demonstrate two new design interfaces that use importance prediction, including a tool for adjusting the relative importance of design elements, and a tool for reflowing designs to new aspect ratios while preserving visual importance.
Paper image

UMSI is able to predict human attention on both natural images and graphic designs. Its performance is comparable to state-of-the-art models specifically built for natural image saliency and it outperforms the existing visual importance models.


Imp1k is a dataset of 1000 designs, covering webpages, movie posters, mobile UIs, infographics and advertisements, for which we have crowdsourced importance annotations using the ImportAnnots interface. Both the dataset and interface are made available.
Dataset image

Example images and corresponding ground truth importance maps from the Imp1k dataset.


We provide code for training and evaluating our model. Our pretrained model weights are available for download.
Code/Models image

Architecture for UMSI model.