paper-with-me

홈 › Papers

Generalization of CNNs on Relational Reasoning with Bar Charts

2025-02-28 · Zhenxing Cui, Lu Chen, Yunhai Wang, Daniel Haehn, Yong Wang, Hanspeter Pfister

This paper presents a systematic study of the generalization of convolutional neural networks (CNNs) and humans on relational reasoning tasks with bar charts. We first revisit previous experiments on graphical perception and update the benchmark performance of CNNs. We then test the generalization performance of CNNs on a classic relational reasoning task: estimating bar length ratios in a bar chart, by progressively perturbing the standard visualizations. We further conduct a user study to compare the performance of CNNs and humans. Our results show that CNNs outperform humans only when the training and test data have the same visual encodings. Otherwise, they may perform worse. We also find that CNNs are sensitive to perturbations in various visual encodings, regardless of their relevance to the target bars. Yet, humans are mainly influenced by bar lengths. Our study suggests that robust relational reasoning with visualizations is challenging for CNNs. Improving CNNs' generalization performance may require training them to better recognize task-related visual properties.

📄 PDF Abstract BibTeX arXiv:2503.00086

Code (1)

ideas-laboratory/graphical-perception 공식 구현 pytorch

Tasks

Relational Reasoning

Similar Papers 제목 키워드 기반

Graph-to-Vision: Multi-graph Understanding and Reasoning using Vision-Language Models

2025-03-27 · Ruizhou Li, Haiyun Jiang

Graph Neural Networks (GNNs), as the dominant paradigm for graph-structured learning, have long faced dual challenges of exponentially escalating computational complexity and inadequate cross-scenario generalization capa…

Graph LearningKnowledge GraphsRelational Reasoning

ChartSketcher: Reasoning with Multimodal Feedback and Reflection for Chart Understanding

2025-05-25 · Muye Huang, Lingling Zhang, Jie Ma, Han Lai 외

Charts are high-density visualization carriers for complex data, serving as a crucial medium for information extraction and analysis. Automated chart understanding poses significant challenges to existing multimodal larg…

Chart UnderstandingLogical Reasoningmultimodal interactionVisual Reasoning

A Saliency-based Convolutional Neural Network for Table and Chart Detection in Digitized Documents

2018-04-17 · I. Kavasidis, S. Palazzo, C. Spampinato, C. Pino 외

Deep Convolutional Neural Networks (DCNNs) have recently been applied successfully to a variety of vision and multimedia tasks, thus driving development of novel solutions in several application domains. Document analysi…

BigCharts-R1: Enhanced Chart Reasoning with Visual Reinforcement Finetuning

2025-08-13 · Ahmed Masry, Abhay Puri, Masoud Hashemi, Juan A. Rodriguez 외 arxiv

Charts are essential to data analysis, transforming raw data into clear visual representations that support human decision-making. Although current vision-language models (VLMs) have made significant progress, they conti…

Reinforcement Learning

Do MLLMs Really Understand the Charts?

2025-08-27 · Xiao Zhang, Dongyuan Li, Liuyu Xiang, Yao Zhang 외 arxiv

Although Multimodal Large Language Models (MLLMs) have demonstrated increasingly impressive performance in chart understanding, most of them exhibit alarming hallucinations and significant performance degradation when ha…

Visual Reasoning