StructChart: On the Schema, Metric, and Augmentation for Visual Chart Understanding

• URL: http://arxiv.org/abs/2309.11268v5
• Date: Wed, 04 Dec 2024 12:43:30 GMT
• Title: StructChart: On the Schema, Metric, and Augmentation for Visual Chart Understanding
• Authors: Renqiu Xia, Haoyang Peng, Hancheng Ye, Mingsheng Li, Xiangchao Yan, Peng Ye, Botian Shi, Yu Qiao, Junchi Yan, Bo Zhang,
• Abstract summary: Current chart-related tasks focus on either chart perception that extracts information from the visual charts, or chart reasoning given the extracted data. We introduce StructChart, a novel framework that leverages Structured Triplet Representations (STR) to achieve a unified and label-efficient approach.
• Score: 54.45681512355684
• License:
• Abstract: Charts are common in literature across various scientific fields, conveying rich information easily accessible to readers. Current chart-related tasks focus on either chart perception that extracts information from the visual charts, or chart reasoning given the extracted data, e.g. in a tabular form. In this paper, we introduce StructChart, a novel framework that leverages Structured Triplet Representations (STR) to achieve a unified and label-efficient approach to chart perception and reasoning tasks, which is generally applicable to different downstream tasks, beyond the question-answering task as specifically studied in peer works. Specifically, StructChart first reformulates the chart data from the tubular form (linearized CSV) to STR, which can friendlily reduce the task gap between chart perception and reasoning. We then propose a Structuring Chart-oriented Representation Metric (SCRM) to quantitatively evaluate the chart perception task performance. To augment the training, we further explore the potential of Large Language Models (LLMs) to enhance the diversity in both chart visual style and statistical information. Extensive experiments on various chart-related tasks demonstrate the effectiveness and potential of a unified chart perception-reasoning paradigm to push the frontier of chart understanding.

Related papers

• ChartAdapter: Large Vision-Language Model for Chart Summarization [13.499376163294816]
  ChartAdapter is a lightweight transformer module designed to bridge the gap between charts and textual summaries. By integrating ChartAdapter with an LLM, we enable end-to-end training and efficient chart summarization.
  arXiv  Detail & Related papers  (2024-12-30T05:07:34Z)
• AskChart: Universal Chart Understanding through Textual Enhancement [20.075911012193494]
  State-of-the-art approaches primarily focus on visual cues from chart images, failing to explicitly incorporate rich textual information embedded within the charts. We introduce AskChart, a universal model that explicitly integrates both textual and visual cues from charts using a Mixture of Experts (MoE) architecture.
  arXiv  Detail & Related papers  (2024-12-26T09:59:43Z)
• On Pre-training of Multimodal Language Models Customized for Chart Understanding [83.99377088129282]
  This paper explores the training processes necessary to improve MLLMs' comprehension of charts. We introduce CHOPINLLM, an MLLM tailored for in-depth chart comprehension.
  arXiv  Detail & Related papers  (2024-07-19T17:58:36Z)
• ChartAssisstant: A Universal Chart Multimodal Language Model via Chart-to-Table Pre-training and Multitask Instruction Tuning [54.89249749894061]
  ChartAssistant is a vision-language model for universal chart comprehension and reasoning. It undergoes a two-stage training process, starting with pre-training on chart-to-table parsing to align chart and text. Experimental results demonstrate significant performance gains over the state-of-the-art UniChart and Chartllama method.
  arXiv  Detail & Related papers  (2024-01-04T17:51:48Z)
• ChartLlama: A Multimodal LLM for Chart Understanding and Generation [70.1393163657813]
  We create a high-quality instruction-tuning dataset leveraging GPT-4. Next, we introduce ChartLlama, a multi-modal large language model that we've trained using our created dataset.
  arXiv  Detail & Related papers  (2023-11-27T15:20:23Z)
• Enhanced Chart Understanding in Vision and Language Task via Cross-modal Pre-training on Plot Table Pairs [71.55796212450055]
  We introduce ChartT5, a V+L model that learns how to interpret table information from chart images via cross-modal pre-training on plot table pairs. Specifically, we propose two novel pre-training objectives: Masked Header Prediction (MHP) and Masked Value Prediction (MVP)
  arXiv  Detail & Related papers  (2023-05-29T22:29:03Z)
• UniChart: A Universal Vision-language Pretrained Model for Chart Comprehension and Reasoning [29.947053208614246]
  We present UniChart, a pretrained model for chart comprehension and reasoning. UniChart encodes the relevant text, data, and visual elements of charts and then uses a chart-grounded text decoder to generate the expected output in natural language. We propose several chart-specific pretraining tasks that include: (i) low-level tasks to extract the visual elements (e.g., bars, lines) and data from charts, and (ii) high-level tasks to acquire chart understanding and reasoning skills.
  arXiv  Detail & Related papers  (2023-05-24T06:11:17Z)
• ChartReader: A Unified Framework for Chart Derendering and Comprehension without Heuristic Rules [89.75395046894809]
  We present ChartReader, a unified framework that seamlessly integrates chart derendering and comprehension tasks. Our approach includes a transformer-based chart component detection module and an extended pre-trained vision-language model for chart-to-X tasks. Our proposed framework can significantly reduce the manual effort involved in chart analysis, providing a step towards a universal chart understanding model.
  arXiv  Detail & Related papers  (2023-04-05T00:25:27Z)

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.