ScatterNet: A Deep Subjective Similarity Model for Visual Analysis of Scatterplots

@article{Ma2020ScatterNetAD,
  title={ScatterNet: A Deep Subjective Similarity Model for Visual Analysis of Scatterplots},
  author={Yuxin Ma and Anthony K. H. Tung and Wei Wang and Xiang Gao and Zhigeng Pan and Wei Chen},
  journal={IEEE Transactions on Visualization and Computer Graphics},
  year={2020},
  volume={26},
  pages={1562-1576}
}
  • Yuxin Ma, A. Tung, +3 authors W. Chen
  • Published 2020
  • Computer Science, Medicine
  • IEEE Transactions on Visualization and Computer Graphics
Similarity measuring methods are widely adopted in a broad range of visualization applications. In this work, we address the challenge of representing human perception in the visual analysis of scatterplots by introducing a novel deep-learning-based approach, ScatterNet, captures perception-driven similarities of such plots. The approach exploits deep neural networks to extract semantic features of scatterplot images for similarity calculation. We create a large labeled dataset consisting of… Expand
Learning a Perceptual Quality Metric for Correlation in Scatterplots
TLDR
A new perception-based quality metric using deep learning that rates the correlation of data dimensions visualized by scatterplots that is able to represent human perception more accurately than previous methods is proposed. Expand
ScagCNN: Estimating Visual Characterizations of 2D Scatterplots via Convolution Neural Network
TLDR
This work provides a machine learning model, called ScagCNN, to estimate the scagnostics scores and provides a web prototype to explore the predictive performance of the model and to give a visual explanation about whether a prediction is accurate. Expand
ClustRank: a Visual Quality Measure Trained on Perceptual Data for Sorting Scatterplots by Cluster Patterns
TLDR
ClustRank improves on existing VQM techniques by mimicking human judgments on two-Gaussian cluster patterns, and gives more accuracy when ranking general cluster patterns in scatterplots. Expand
Toward Perception-Based Evaluation of Clustering Techniques for Visual Analytics
TLDR
A more systematic way of evaluating clustering algorithms based on quantification of human perception of clusters in 2D scatterplots is proposed, and how this could lead to the design of perception-based clustering techniques that would better support more trustworthy and explainable models of cluster patterns. Expand
Disentangled Representation of Data Distributions in Scatterplots
TLDR
A data-driven approach is presented to obtain a disentangled and interpretable representation that can characterize bivariate data distributions of scatterplots and finds Pearson’s correlation coefficient between the predicted and perceptual distances was above 0.75, which indicates the effectiveness of the representation in the quantitative characterization of scatter Plots. Expand
Deep Colormap Extraction from Visualizations
TLDR
This work presents a new approach based on deep learning to automatically extract colormaps from visualizations by passing the histogram of colors in an input visualization image to a pre-trained deep neural network, which learns to predict the colormap that produces the visualization. Expand
Evaluating Perceptual Bias During Geometric Scaling of Scatterplots
TLDR
An evaluation study on the perceptual bias of visual features in scatterplots caused by geometric scaling focuses on three fundamental visual features (i.e., numerosity, correlation, and cluster separation) and three hypotheses that are formulated on the basis of the experience. Expand
Visual Abstraction of Geographical Point Data with Spatial Autocorrelations
TLDR
A novel attribute-based sampling model is designed to generate a subset of points to preserve both density and attribute characteristics of original geographical points and a set of visual designs and user-friendly interactions are implemented, enabling users to capture the spatial distribution of geographical points. Expand
An Automated Approach to Reasoning About Task-Oriented Insights in Responsive Visualization
TLDR
An automated approach to approximating the loss of support for task-oriented visualization insights (identification, comparison, and trend) in responsive transformation of a source visualization is proposed. Expand
Peax: Interactive Visual Pattern Search in Sequential Data Using Unsupervised Deep Representation Learning
TLDR
A convolutional autoencoder for unsupervised representation learning of regions in sequential data that can capture more visual details of complex patterns compared to existing similarity measures is developed. Expand
...
1
2
3
4
...

References

SHOWING 1-10 OF 63 REFERENCES
Visual Abstraction and Exploration of Multi-class Scatterplots
  • Haidong Chen, W. Chen, +5 authors K. Ma
  • Computer Science, Medicine
  • IEEE Transactions on Visualization and Computer Graphics
  • 2014
TLDR
A new visual abstraction scheme is presented that employs a hierarchical multi-class sampling technique to show a feature-preserving simplification and to enhance the density contrast, the colors of multiple classes are optimized by taking the multi- class point distributions into account. Expand
Guiding the Exploration of Scatter Plot Data Using Motif-Based Interest Measures
TLDR
Inspired by the well-known tf-idf approach from information retrieval, local and global quality measures based on certain frequency properties of the local motifs are computed and used to filter, rank and compare scatter plots and their incorporated motifs. Expand
Cluster-Based Visual Abstraction for Multivariate Scatterplots
TLDR
This study presents a cluster-based visual abstraction method that leverages an adapted multilabel clustering method to provide abstractions of high quality for scatterplots and a suite of glyphs designed to visualize the data at different levels of detail and support data exploration. Expand
Towards Understanding Human Similarity Perception in the Analysis of Large Sets of Scatter Plots
TLDR
A study aimed at understanding how human observers judge scatter plot similarity when presented with a large set of iconic scatter plot representations and a list of concepts derived to describe major perceptual features and how these concepts relate and rank. Expand
Magnostics: Image-Based Search of Interesting Matrix Views for Guided Network Exploration
TLDR
This work addresses the problem of retrieving potentially interesting matrix views to support the exploration of networks by evaluating 30 feature descriptors for matrix diagnostics and concludes with an informed set of six descriptors as most appropriate for Magnostics. Expand
Learning Perceptual Kernels for Visualization Design
TLDR
This work introduces perceptual kernels: distance matrices derived from aggregate perceptual judgments, which represent perceptual differences between and within visual variables in a reusable form that is directly applicable to visualization evaluation and automated design. Expand
Visual Analytics for Spatial Clustering: Using a Heuristic Approach for Guided Exploration
We propose a novel approach of distance-based spatial clustering and contribute a heuristic computation of input parameters for guiding users in the search of interesting cluster constellations. WeExpand
Guided Sketching for Visual Search and Exploration in Large Scatter Plot Spaces
TLDR
An approach for explorative search and navigation in large sets of scatter plot diagrams by means of a sketch-based query interface, which provides suggestions for possibly relevant patterns while query drawing takes place, supporting the visual search process. Expand
A Taxonomy of Visual Cluster Separation Factors
TLDR
A taxonomy of visual cluster separation factors in scatterplots, and an in‐depth qualitative evaluation of two recently proposed and validated separation measures are provided. Expand
Ranking Visualizations of Correlation Using Weber's Law
TLDR
A large scale crowdsourced experiment is conducted to investigate whether the perception of correlation in nine commonly used visualizations can be modeled using Weber's law, establishing that for all tested visualizations, the precision of correlation judgment could be modeled by Weber'sLaw. Expand
...
1
2
3
4
5
...