Judging the similarity of visualizations is crucial to various applications, such as visualization-based search and visualization recommendation systems. Recent studies show deep-feature-based similarity metrics correlate well with perceptual judgments of image similarity and serve as effective loss functions for tasks like image super-resolution and style transfer. We explore the application of such metrics to judgments of visualization similarity. We extend a similarity metric using five ML architectures and three pre-trained weight sets. We replicate results from previous crowd-sourced studies on scatterplot and visual channel similarity perception. Notably, our metric using pre-trained ImageNet weights outperformed gradient-descent tuned MS-SSIM, a multi-scale similarity metric based on luminance, contrast, and structure. Our work contributes to understanding how deep-feature-based metrics can enhance similarity assessments in visualization, potentially improving visual analysis tools and techniques. Supplementary materials are available atthis https URL.
View on arXiv@article{long2025_2503.00228,
title={ Seeing Eye to AI? Applying Deep-Feature-Based Similarity Metrics to Information Visualization },
author={ Sheng Long and Angelos Chatzimparmpas and Emma Alexander and Matthew Kay and Jessica Hullman },
journal={arXiv preprint arXiv:2503.00228},
year={ 2025 }
}