ChartAssisstant: A Universal Chart Multimodal Language Model via Chart-to-Table Pre-training and Multitask Instruction Tuning

2024/01/04 by Meng, Fanqing, Shao, Wenqi, Lu, Quanfeng +4 · 16 citations
#Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences

paper · doi:10.48550/arxiv.2401.02384

Abstract

Charts play a vital role in data visualization, understanding data patterns, and informed decision-making. However, their unique combination of graphical elements (e.g., bars, lines) and textual components (e.g., labels, legends) poses challenges for general-purpose multimodal models. While vision-language models trained on chart data excel in comprehension, they struggle with generalization. To address these challenges, we propose ChartAssistant, a chart-based vision-language model for universal chart comprehension and reasoning. ChartAssistant leverages ChartSFT, a comprehensive dataset covering diverse chart-related tasks with basic (e.g. bars and pies) and specialized (e.g. radars, and bubbles) chart types. It undergoes a two-stage training process, starting with pre-training on chart-to-table parsing to align chart and text, followed by multitask instruction-following fine-tuning. This approach enables ChartAssistant to achieve competitive performance across various chart tasks. Experimental results demonstrate significant performance gains over the state-of-the-art UniChart and Chartllama method, especially outperforming them on real-world chart data with zero-shot setting. The code and data are available at https://github.com/OpenGVLab/ChartAst.

Cited by

• CycleChart: A Unified Consistency-Based Learning Framework for Bidirectional Chart Understanding and Generation
• ChartM³: A Multi-Stage Code-Driven Pipeline for Constructing Multi-Dimensional and Multi-Step Visual Reasoning Data in Chart Comprehension
• ChartAB: A Benchmark for Chart Grounding & Dense Alignment
• ChartNet: A Million-Scale, High-Quality Multimodal Dataset for Robust Chart Understanding
• Composition-Grounded Instruction Synthesis for Visual Reasoning
• Autonomous Agents for Scientific Discovery: Orchestrating Scientists, Language, Code, and Physics
• Benchmark It Yourself (BIY): Preparing a Dataset and Benchmarking AI Models for Scatterplot-Related Tasks
• PixelCraft: A Multi-Agent System for High-Fidelity Visual Reasoning on Structured Images
• Large Language Models for Accessible Reporting of Bioinformatics Analyses in Interdisciplinary Contexts
• Losing the Plot: How VLM responses degrade on imperfect charts
• ChartMaster: Advancing Chart-to-Code Generation with Real-World Charts and Chart Similarity Reinforcement Learning
• MindVL: Towards Efficient and Effective Training of Multimodal Large Language Models on Ascend NPUs
• Visual Programmability: A Guide for Code-as-Thought in Chart Understanding
• Chart-CoCa: Self-Improving Chart Understanding of Vision LMs via Code-Driven Synthesis and Candidate-Conditioned Answering
• Effective Training Data Synthesis for Improving MLLM Chart Understanding
• ChartCap: Mitigating Hallucination of Dense Chart Captioning

Related

• ChartLlama: A Multimodal LLM for Chart Understanding and Generation
• UniChart: A Universal Vision-language Pretrained Model for Chart Comprehension and Reasoning
• MMC: Advancing Multimodal Chart Understanding with Large-scale Instruction Tuning
• In-Depth and In-Breadth: Pre-training Multimodal Language Models Customized for Comprehensive Chart Understanding
• On Pre-training of Multimodal Language Models Customized for Chart Understanding