AltChart: Enhancing VLM-based Chart Summarization Through Multi-Pretext Tasks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Moured, Omar, Zhang, Jiaming, Sarfraz, M. Saquib, Stiefelhagen, Rainer
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910079963365376
author Moured, Omar
Zhang, Jiaming
Sarfraz, M. Saquib
Stiefelhagen, Rainer
author_facet Moured, Omar
Zhang, Jiaming
Sarfraz, M. Saquib
Stiefelhagen, Rainer
contents Chart summarization is a crucial task for blind and visually impaired individuals as it is their primary means of accessing and interpreting graphical data. Crafting high-quality descriptions is challenging because it requires precise communication of essential details within the chart without vision perception. Many chart analysis methods, however, produce brief, unstructured responses that may contain significant hallucinations, affecting their reliability for blind people. To address these challenges, this work presents three key contributions: (1) We introduce the AltChart dataset, comprising 10,000 real chart images, each paired with a comprehensive summary that features long-context, and semantically rich annotations. (2) We propose a new method for pretraining Vision-Language Models (VLMs) to learn fine-grained chart representations through training with multiple pretext tasks, yielding a performance gain with ${\sim}2.5\%$. (3) We conduct extensive evaluations of four leading chart summarization models, analyzing how accessible their descriptions are. Our dataset and codes are publicly available on our project page: https://github.com/moured/AltChart.
format Preprint
id arxiv_https___arxiv_org_abs_2405_13580
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle AltChart: Enhancing VLM-based Chart Summarization Through Multi-Pretext Tasks
Moured, Omar
Zhang, Jiaming
Sarfraz, M. Saquib
Stiefelhagen, Rainer
Computer Vision and Pattern Recognition
Human-Computer Interaction
Chart summarization is a crucial task for blind and visually impaired individuals as it is their primary means of accessing and interpreting graphical data. Crafting high-quality descriptions is challenging because it requires precise communication of essential details within the chart without vision perception. Many chart analysis methods, however, produce brief, unstructured responses that may contain significant hallucinations, affecting their reliability for blind people. To address these challenges, this work presents three key contributions: (1) We introduce the AltChart dataset, comprising 10,000 real chart images, each paired with a comprehensive summary that features long-context, and semantically rich annotations. (2) We propose a new method for pretraining Vision-Language Models (VLMs) to learn fine-grained chart representations through training with multiple pretext tasks, yielding a performance gain with ${\sim}2.5\%$. (3) We conduct extensive evaluations of four leading chart summarization models, analyzing how accessible their descriptions are. Our dataset and codes are publicly available on our project page: https://github.com/moured/AltChart.
title AltChart: Enhancing VLM-based Chart Summarization Through Multi-Pretext Tasks
topic Computer Vision and Pattern Recognition
Human-Computer Interaction
url https://arxiv.org/abs/2405.13580