Publications

Fast and Accurate CNN-based Brushing in Scatterplots

C. Fan and H. Hauser

Abstract

Brushing plays a central role in most modern visual analytics solutions and effective and efficient techniques for data selection are key to establishing a successful human-computer dialogue. With this paper, we address the need for brushing techniques that are both fast, enabling a fluid interaction in visual data exploration and analysis, and also accurate, i.e., enabling the user to effectively select specific data subsets, even when their geometric delimination is non-trivial. We present a new solution for a near-perfect sketch-based brushing technique, where we exploit a convolutional neural network (CNN) for estimating the intended data selection from a fast and simple click-and-drag interaction and from the data distribution in the visualization. Our key contributions include a drastically reduced error rate-now below 3%, i.e., less than half of the so far best accuracy- and an extension to a larger variety of selected data subsets, going beyond previous limitations due to linear estimation models.

C. Fan and H. Hauser, "Fast and Accurate CNN-based Brushing in Scatterplots," Computer Graphics Forum (Eurovis 2018), 2018. doi:10.1111/cgf.13405
[BibTeX]

Brushing plays a central role in most modern visual analytics solutions and effective and efficient techniques for data selection are key to establishing a successful human-computer dialogue. With this paper, we address the need for brushing techniques that are both fast, enabling a fluid interaction in visual data exploration and analysis, and also accurate, i.e., enabling the user to effectively select specific data subsets, even when their geometric delimination is non-trivial. We present a new solution for a near-perfect sketch-based brushing technique, where we exploit a convolutional neural network (CNN) for estimating the intended data selection from a fast and simple click-and-drag interaction and from the data distribution in the visualization. Our key contributions include a drastically reduced error rate-now below 3%, i.e., less than half of the so far best accuracy- and an extension to a larger variety of selected data subsets, going beyond previous limitations due to linear estimation models.
@ARTICLE {cnn-brush,
author = "Fan, Chaoran and Hauser, Helwig",
title = "{Fast and Accurate CNN-based Brushing in Scatterplots}",
journal = "Computer Graphics Forum (Eurovis 2018)",
year = "2018",
abstract = "Brushing plays a central role in most modern visual analytics solutions and effective and efficient techniques for data selection are key to establishing a successful human-computer dialogue. With this paper, we address the need for brushing techniques that are both fast, enabling a fluid interaction in visual data exploration and analysis, and also accurate, i.e., enabling the user to effectively select specific data subsets, even when their geometric delimination is non-trivial. We present a new solution for a near-perfect sketch-based brushing technique, where we exploit a convolutional neural network (CNN) for estimating the intended data selection from a fast and simple click-and-drag interaction and from the data distribution in the visualization. Our key contributions include a drastically reduced error rate-now below 3%, i.e., less than half of the so far best accuracy- and an extension to a larger variety of selected data subsets, going beyond previous limitations due to linear estimation models.",
pdf = "pdfs/eurovis18.pdf",
images = "images/cnn.png",
thumbnails = "images/cnn.png",
publisher = "The Eurographics Association and John Wiley and Sons Ltd.",
issn = "1467-8659",
doi = "10.1111/cgf.13405"
}
projectidprojectid

Media

Downloads

Full paper [PDF]