Evaluating Graphical Perception Capabilities of Vision Transformers
This work addresses the problem of understanding ViTs' perceptual capabilities for visualization systems, but it is incremental as it extends existing evaluation methods from CNNs to ViTs.
The study evaluated Vision Transformers (ViTs) on graphical perception tasks, inspired by Cleveland and McGill, and found that while ViTs perform well in general vision, their alignment with human-like perception in visualization is limited.
Vision Transformers, ViTs, have emerged as a powerful alternative to convolutional neural networks, CNNs, in a variety of image-based tasks. While CNNs have previously been evaluated for their ability to perform graphical perception tasks, which are essential for interpreting visualizations, the perceptual capabilities of ViTs remain largely unexplored. In this work, we investigate the performance of ViTs in elementary visual judgment tasks inspired by the foundational studies of Cleveland and McGill, which quantified the accuracy of human perception across different visual encodings. Inspired by their study, we benchmark ViTs against CNNs and human participants in a series of controlled graphical perception tasks. Our results reveal that, although ViTs demonstrate strong performance in general vision tasks, their alignment with human-like graphical perception in the visualization domain is limited. This study highlights key perceptual gaps and points to important considerations for the application of ViTs in visualization systems and graphical perceptual modeling.