UIBert: Learning Generic Multimodal Representations for UI Understanding

• URL: http://arxiv.org/abs/2107.13731v1
• Date: Thu, 29 Jul 2021 03:51:36 GMT
• Title: UIBert: Learning Generic Multimodal Representations for UI Understanding
• Authors: Chongyang Bai, Xiaoxue Zang, Ying Xu, Srinivas Sunkara, Abhinav Rastogi, Jindong Chen, Blaise Aguera y Arcas
• Abstract summary: We introduce a transformer-based joint image-text model trained through novel pre-training tasks on large-scale unlabeled UI data. Our key intuition is that the heterogeneous features in a UI are self-aligned, i.e., the image and text features of UI components, are predictive of each other. We propose five pretraining tasks utilizing this self-alignment among different features of a UI component and across various components in the same UI. We evaluate our method on nine real-world downstream UI tasks where UIBert outperforms strong multimodal baselines by up to 9.26% accuracy.
• Score: 12.931540149350633
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: To improve the accessibility of smart devices and to simplify their usage, building models which understand user interfaces (UIs) and assist users to complete their tasks is critical. However, unique challenges are proposed by UI-specific characteristics, such as how to effectively leverage multimodal UI features that involve image, text, and structural metadata and how to achieve good performance when high-quality labeled data is unavailable. To address such challenges we introduce UIBert, a transformer-based joint image-text model trained through novel pre-training tasks on large-scale unlabeled UI data to learn generic feature representations for a UI and its components. Our key intuition is that the heterogeneous features in a UI are self-aligned, i.e., the image and text features of UI components, are predictive of each other. We propose five pretraining tasks utilizing this self-alignment among different features of a UI component and across various components in the same UI. We evaluate our method on nine real-world downstream UI tasks where UIBert outperforms strong multimodal baselines by up to 9.26% accuracy.

Related papers

• Harnessing Webpage UIs for Text-Rich Visual Understanding [112.01029887404296]
  We propose synthesizing general multimodal instructions from webpage UIs using text-based large language models (LLMs) These instructions are then paired with UI screenshots to train multimodal models. We introduce MultiUI, a dataset containing 7.3 million samples from 1 million websites, covering diverse multimodal tasks and UI layouts.
  arXiv  Detail & Related papers  (2024-10-17T17:48:54Z)
• AMEX: Android Multi-annotation Expo Dataset for Mobile GUI Agents [50.39555842254652]
  We introduce the Android Multi-annotation EXpo (AMEX) to advance research on AI agents in mobile scenarios. AMEX comprises over 104K high-resolution screenshots from 110 popular mobile applications, which are annotated at multiple levels. AMEX includes three levels of annotations: GUI interactive element grounding, GUI screen and element functionality descriptions, and complex natural language instructions.
  arXiv  Detail & Related papers  (2024-07-03T17:59:58Z)
• GUI-WORLD: A Dataset for GUI-oriented Multimodal LLM-based Agents [73.9254861755974]
  This paper introduces a new dataset, called GUI-World, which features meticulously crafted Human-MLLM annotations. We evaluate the capabilities of current state-of-the-art MLLMs, including ImageLLMs and VideoLLMs, in understanding various types of GUI content.
  arXiv  Detail & Related papers  (2024-06-16T06:56:53Z)
• Tell Me What's Next: Textual Foresight for Generic UI Representations [65.10591722192609]
  We propose Textual Foresight, a novel pretraining objective for learning UI screen representations. Textual Foresight generates global text descriptions of future UI states given a current UI and local action taken. We train with our newly constructed mobile app dataset, OpenApp, which results in the first public dataset for app UI representation learning.
  arXiv  Detail & Related papers  (2024-06-12T02:43:19Z)
• UIClip: A Data-driven Model for Assessing User Interface Design [20.66914084220734]
  We develop a machine-learned model, UIClip, for assessing the design quality and visual relevance of a user interface. We show how UIClip can facilitate downstream applications that rely on instantaneous assessment of UI design quality.
  arXiv  Detail & Related papers  (2024-04-18T20:43:08Z)
• UI Semantic Group Detection: Grouping UI Elements with Similar Semantics in Mobile Graphical User Interface [10.80156450091773]
  Existing studies on UI elements grouping mainly focus on a single UI-related software engineering task, and their groups vary in appearance and function. We propose our semantic component groups that pack adjacent text and non-text elements with similar semantics. To recognize semantic component groups on a UI page, we propose a robust, deep learning-based vision detector, UISCGD.
  arXiv  Detail & Related papers  (2024-03-08T01:52:44Z)
• ILuvUI: Instruction-tuned LangUage-Vision modeling of UIs from Machine Conversations [13.939350184164017]
  Multimodal Vision-Language Models (VLMs) enable powerful applications from their fused understanding of images and language. We adapt a recipe for generating paired text-image training data for VLMs to the UI domain by combining existing pixel-based methods with a Large Language Model (LLM) We generate a dataset of 335K conversational examples paired with UIs that cover Q&A, UI descriptions, and planning, and use it to fine-tune a conversational VLM for UI tasks.
  arXiv  Detail & Related papers  (2023-10-07T16:32:34Z)
• VINS: Visual Search for Mobile User Interface Design [66.28088601689069]
  This paper introduces VINS, a visual search framework, that takes as input a UI image and retrieves visually similar design examples. The framework achieves a mean Average Precision of 76.39% for the UI detection and high performance in querying similar UI designs.
  arXiv  Detail & Related papers  (2021-02-10T01:46:33Z)
• ActionBert: Leveraging User Actions for Semantic Understanding of User Interfaces [12.52699475631247]
  We introduce a new pre-trained UI representation model called ActionBert. Our methodology is designed to leverage visual, linguistic and domain-specific features in user interaction traces to pre-train generic feature representations of UIs and their components. Experiments show that the proposed ActionBert model outperforms multi-modal baselines across all downstream tasks by up to 15.5%.
  arXiv  Detail & Related papers  (2020-12-22T20:49:52Z)
• User-Guided Domain Adaptation for Rapid Annotation from User Interactions: A Study on Pathological Liver Segmentation [49.96706092808873]
  Mask-based annotation of medical images, especially for 3D data, is a bottleneck in developing reliable machine learning models. We propose the user-guided domain adaptation (UGDA) framework, which uses prediction-based adversarial domain adaptation (PADA) to model the combined distribution of UIs and mask predictions. We show UGDA can retain this state-of-the-art performance even when only seeing a fraction of available UIs.
  arXiv  Detail & Related papers  (2020-09-05T04:24:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.