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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Baechler, Gilles, Sunkara, Srinivas, Wang, Maria, Zubach, Fedir, Mansoor, Hassan, Etter, Vincent, Cărbune, Victor, Lin, Jason, Chen, Jindong, Sharma, Abhanshu
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913416161001472
author Baechler, Gilles
Sunkara, Srinivas
Wang, Maria
Zubach, Fedir
Mansoor, Hassan
Etter, Vincent
Cărbune, Victor
Lin, Jason
Chen, Jindong
Sharma, Abhanshu
author_facet Baechler, Gilles
Sunkara, Srinivas
Wang, Maria
Zubach, Fedir
Mansoor, Hassan
Etter, Vincent
Cărbune, Victor
Lin, Jason
Chen, Jindong
Sharma, Abhanshu
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2402_04615
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle ScreenAI: A Vision-Language Model for UI and Infographics Understanding
Baechler, Gilles
Sunkara, Srinivas
Wang, Maria
Zubach, Fedir
Mansoor, Hassan
Etter, Vincent
Cărbune, Victor
Lin, Jason
Chen, Jindong
Sharma, Abhanshu
Computer Vision and Pattern Recognition
Artificial Intelligence
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.
title ScreenAI: A Vision-Language Model for UI and Infographics Understanding
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2402.04615