Lexi: Self-Supervised Learning of the UI Language

TL;DR

Lexi is a self-supervised vision-language model trained on a large UI dataset, enabling better understanding of UI screens for applications like accessibility and automation without relying on UI metadata.

Contribution

We introduce Lexi, a novel pre-trained vision-language model for UI understanding that does not depend on UI metadata, trained on a large curated dataset.

Findings

Lexi outperforms existing models on UI action entailment.

Lexi achieves high accuracy in instruction-based UI image retrieval.

Lexi effectively grounds referring expressions and recognizes UI entities.

Abstract

Humans can learn to operate the user interface (UI) of an application by reading an instruction manual or how-to guide. Along with text, these resources include visual content such as UI screenshots and images of application icons referenced in the text. We explore how to leverage this data to learn generic visio-linguistic representations of UI screens and their components. These representations are useful in many real applications, such as accessibility, voice navigation, and task automation. Prior UI representation models rely on UI metadata (UI trees and accessibility labels), which is often missing, incompletely defined, or not accessible. We avoid such a dependency, and propose Lexi, a pre-trained vision and language model designed to handle the unique features of UI screens, including their text richness and context sensitivity. To train Lexi we curate the UICaption dataset consisting of 114k UI images paired with descriptions of their functionality. We evaluate Lexi on four tasks: UI action entailment, instruction-based UI image retrieval, grounding referring expressions, and UI entity recognition.