ScreenAI: A Vision-Language Model for UI and Infographics Understanding

TL;DR

ScreenAI is a vision-language model designed for understanding user interfaces and infographics, leveraging novel training strategies and datasets to achieve state-of-the-art performance on multiple UI and infographic tasks.

Contribution

The paper introduces ScreenAI, a specialized vision-language model with a novel screen annotation task and scalable dataset generation, improving UI and infographic understanding.

Findings

Achieves state-of-the-art results on multiple UI and infographic tasks

Uses a novel screen annotation task for training

Releases three new datasets for UI understanding

Abstract

Screen user interfaces (UIs) and infographics, sharing similar visual language and design principles, play important roles in human communication and human-machine interaction. We introduce ScreenAI, a vision-language model that specializes in UI and infographics understanding. Our model improves upon the PaLI architecture with the flexible patching strategy of pix2struct and is trained on a unique mixture of datasets. At the heart of this mixture is a novel screen annotation task in which the model has to identify the type and location of UI elements. We use these text annotations to describe screens to Large Language Models and automatically generate question-answering (QA), UI navigation, and summarization training datasets at scale. We run ablation studies to demonstrate the impact of these design choices. At only 5B parameters, ScreenAI achieves new state-of-the-artresults on UI- and infographics-based tasks (Multi-page DocVQA, WebSRC, MoTIF and Widget Captioning), and new best-in-class performance on others (Chart QA, DocVQA, and InfographicVQA) compared to models of similar size. Finally, we release three new datasets: one focused on the screen annotation task and two others focused on question answering.