Graphical Perception of Saliency-based Model Explanations
This work addresses the challenge of effectively communicating model explanations to humans in interpretable AI, but it is incremental as it focuses on specific visualization aspects without broad SOTA impact.
The study tackled the problem of how visualization design affects human perception of saliency-based explanations for visual recognition models, finding that factors like design decisions, alignment type, and saliency map qualities significantly influence perception.
In recent years, considerable work has been devoted to explaining predictive, deep learning-based models, and in turn how to evaluate explanations. An important class of evaluation methods are ones that are human-centered, which typically require the communication of explanations through visualizations. And while visualization plays a critical role in perceiving and understanding model explanations, how visualization design impacts human perception of explanations remains poorly understood. In this work, we study the graphical perception of model explanations, specifically, saliency-based explanations for visual recognition models. We propose an experimental design to investigate how human perception is influenced by visualization design, wherein we study the task of alignment assessment, or whether a saliency map aligns with an object in an image. Our findings show that factors related to visualization design decisions, the type of alignment, and qualities of the saliency map all play important roles in how humans perceive saliency-based visual explanations.