Beyond End-to-End VLMs: Leveraging Intermediate Text Representations for Superior Flowchart Understanding

• URL: http://arxiv.org/abs/2412.16420v1
• Date: Sat, 21 Dec 2024 00:52:41 GMT
• Title: Beyond End-to-End VLMs: Leveraging Intermediate Text Representations for Superior Flowchart Understanding
• Authors: Junyi Ye, Ankan Dash, Wenpeng Yin, Guiling Wang,
• Abstract summary: Flowcharts are typically presented as images, driving the trend of using vision-language models (VLMs) for end-to-end flowchart understanding. Two key challenges arise: (i) Limited controllability--users have minimal influence over the downstream task, while the training of VLMs is often out of reach. We propose TextFlow, addressing aforementioned issues with two stages: Vision Textualizer and Textual Reasoner.
• Score: 9.267156820352996
• License:
• Abstract: Flowcharts are typically presented as images, driving the trend of using vision-language models (VLMs) for end-to-end flowchart understanding. However, two key challenges arise: (i) Limited controllability--users have minimal influence over the downstream task, as they can only modify input images, while the training of VLMs is often out of reach for most researchers. (ii) Lack of explainability--it is difficult to trace VLM errors to specific causes, such as failures in visual encoding or reasoning. We propose TextFlow, addressing aforementioned issues with two stages: (i) Vision Textualizer--which generates textual representations from flowchart images; and (ii) Textual Reasoner--which performs question-answering based on the text representations. TextFlow offers three key advantages: (i) users can select the type of text representations (e.g., Graphviz, Mermaid, PlantUML), or further convert them into executable graph object to call tools, enhancing performance and controllability; (ii) it improves explainability by helping to attribute errors more clearly to visual or textual processing components; and (iii) it promotes the modularization of the solution, such as allowing advanced LLMs to be used in the Reasoner stage when VLMs underperform in end-to-end fashion. Experiments on the FlowVQA and FlowLearn benchmarks demonstrate TextFlow's state-of-the-art performance as well as its robustness. All code is publicly available.

Related papers

• Overcoming Vision Language Model Challenges in Diagram Understanding: A Proof-of-Concept with XML-Driven Large Language Models Solutions [0.0]
  Diagrams play crucial role in visually conveying complex relationships and processes within business documentation. Despite recent advances in Vision-Language Models (VLMs) for various image understanding tasks, accurately identifying and extracting structures in diagrams continues to pose significant challenges. This study proposes a text-driven approach that bypasses reliance on VLMs' visual recognition capabilities.
  arXiv  Detail & Related papers  (2025-02-05T23:40:26Z)
• Accelerating Multimodal Large Language Models via Dynamic Visual-Token Exit and the Empirical Findings [69.35226485836641]
  Excessive use of visual tokens in existing Multimoal Large Language Models (MLLMs) often exhibits obvious redundancy and brings in prohibitively expensive computation. We propose a simple yet effective method to improve the efficiency of MLLMs, termed dynamic visual-token exit (DyVTE) DyVTE uses lightweight hyper-networks to perceive the text token status and decide the removal of all visual tokens after a certain layer.
  arXiv  Detail & Related papers  (2024-11-29T11:24:23Z)
• FTII-Bench: A Comprehensive Multimodal Benchmark for Flow Text with Image Insertion [7.322448493179106]
  Flow Text with Image Insertion task requires LVLMs to simultaneously possess outstanding abilities in image comprehension, instruction understanding, and long-text interpretation. We introduce the Flow Text with Image Insertion Benchmark (FTII-Bench), which includes 318 high-quality Chinese image-text news articles and 307 high-quality English image-text news articles, covering 10 different news domains. We evaluate 9 open-source and 2 closed-source LVLMs as well as 2 CLIP-based models.
  arXiv  Detail & Related papers  (2024-10-16T13:38:31Z)
• Leopard: A Vision Language Model For Text-Rich Multi-Image Tasks [62.758680527838436]
  Leopard is a vision-language model for handling vision-language tasks involving multiple text-rich images. First, we curated about one million high-quality multimodal instruction-tuning data, tailored to text-rich, multi-image scenarios. Second, we developed an adaptive high-resolution multi-image encoding module to dynamically optimize the allocation of visual sequence length.
  arXiv  Detail & Related papers  (2024-10-02T16:55:01Z)
• FlowLearn: Evaluating Large Vision-Language Models on Flowchart Understanding [52.35520385083425]
  FlowLearn dataset is a resource tailored to enhance the understanding of flowcharts. The scientific subset contains 3,858 flowcharts sourced from scientific literature. The simulated subset contains 10,000 flowcharts created using a customizable script.
  arXiv  Detail & Related papers  (2024-07-06T20:58:51Z)
• Progressive Multi-modal Conditional Prompt Tuning [92.50645776024624]
  Pre-trained vision-language models (VLMs) have shown remarkable generalization capabilities via prompting. We propose a novel method, Progressive Multi-modal conditional Prompt Tuning (ProMPT) ProMPT exploits a recurrent structure, optimizing and aligning V-L features by iteratively utilizing image and current encoding information.
  arXiv  Detail & Related papers  (2024-04-18T02:40:31Z)
• Visually Descriptive Language Model for Vector Graphics Reasoning [76.42082386029206]
  We propose the Visually Descriptive Language Model (VDLM) to bridge the gap between low-level visual perception and high-level language reasoning. We show that VDLM significantly improves state-of-the-art LMMs like GPT-4o on various multimodal perception and reasoning tasks.
  arXiv  Detail & Related papers  (2024-04-09T17:30:18Z)
• VILA: On Pre-training for Visual Language Models [74.08039416548209]
  We study the design options for VLM pre-training through step-by-step controllable comparisons. We build VILA, a Visual Language model family that consistently outperforms the state-of-the-art models.
  arXiv  Detail & Related papers  (2023-12-12T18:58:18Z)
• Which Modality should I use -- Text, Motif, or Image? : Understanding Graphs with Large Language Models [14.251972223585765]
  This paper introduces a new approach to encoding a graph with diverse modalities, such as text, image, and motif, and prompts to approximate a graph's global connectivity. The study also presents GraphTMI, a novel benchmark for evaluating Large Language Models (LLMs) in graph structure analysis.
  arXiv  Detail & Related papers  (2023-11-16T12:45:41Z)

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.