# FigureQA: An Annotated Figure Dataset for Visual Reasoning Source: [FigureQA: An Annotated Figure Dataset for Visual Reasoning]() Collection index: [llms.txt]() Data updated: 2026-01-04T02:54:58.055Z Authors: Samira Ebrahimi Kahou, Vincent Michalski, Adam Atkinson, Akos Kadar, Adam Trischler, Yoshua Bengio Published: 2017-10-19T18:01:38.000Z ## Abstract We introduce FigureQA, a visual reasoning corpus of over one million question-answer pairs grounded in over 100,000 images. The images are synthetic, scientific-style figures from five classes: line plots, dot-line plots, vertical and horizontal bar graphs, and pie charts. We formulate our reasoning task by generating questions from 15 templates; questions concern various relationships between plot elements and examine characteristics like the maximum, the minimum, area-under-the-curve, smoothness, and intersection. To resolve, such questions often require reference to multiple plot elements and synthesis of information distributed spatially throughout a figure. To facilitate the training of machine learning systems, the corpus also includes side data that can be used to formulate auxiliary objectives. In particular, we provide the numerical data used to generate each figure as well as bounding-box annotations for all plot elements. We study the proposed visual reasoning task by training several models, including the recently proposed Relation Network as a strong baseline. Preliminary results indicate that the task poses a significant machine learning challenge. We envision FigureQA as a first step towards developing models that can intuitively recognize patterns from visual representations of data. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Chart Question Answering on FigureQA Alternated Colors (val 2)](): Chart Question Answering; FigureQA Alternated Colors (val 2); Overall Accuracy: 72.54. - [Figure Visual Question Answering on FigureQA 1.0 (test 2)](): Figure Visual Question Answering; FigureQA 1.0 (test 2); Overall Accuracy: 91.21. - [Chart Question Answering on FigureQA Same Colors 1 (val)](): Chart Question Answering; FigureQA Same Colors 1 (val); Accuracy (vBar): 85.71. - [Visual Question Answering on FigureQA Original color scheme (test)](): Visual Question Answering; FigureQA Original color scheme (test); Accuracy: 76.52. - [Chart Question Answering on DVQA Novel (test)](): Chart Question Answering; DVQA novel (test); Structure: 96.19. - [Visual Question Answering on FigureQA Alternate color scheme (test)](): Visual Question Answering; FigureQA Alternate color scheme (test); Accuracy: 72.4. - [Chart Question Answering on DVQA (test-familiar)](): Chart Question Answering; DVQA (test-familiar); Structure: 90.38. - [Visual Question Answering on FigureQA Alternate color scheme (val)](): Visual Question Answering; FigureQA Alternate color scheme (val); Accuracy: 72.54. ## Original sources and implementation [Original paper]() [PDF]() [Implementation]()