Interactivity x Explainability: Toward Understanding How Interactivity Can Improve Computer Vision Explanations
This work tackles the problem of improving interpretability for users of computer vision models, though it is incremental as it builds on existing explanation methods by adding interactivity.
The study investigated how interactivity can address challenges in static computer vision explanations, such as information overload and limited exploration, by testing three explanation types with 24 participants in a bird identification task. It found that interactivity improves user control and understanding but also introduces new challenges, leading to design recommendations like default views and constrained output spaces.
Explanations for computer vision models are important tools for interpreting how the underlying models work. However, they are often presented in static formats, which pose challenges for users, including information overload, a gap between semantic and pixel-level information, and limited opportunities for exploration. We investigate interactivity as a mechanism for tackling these issues in three common explanation types: heatmap-based, concept-based, and prototype-based explanations. We conducted a study (N=24), using a bird identification task, involving participants with diverse technical and domain expertise. We found that while interactivity enhances user control, facilitates rapid convergence to relevant information, and allows users to expand their understanding of the model and explanation, it also introduces new challenges. To address these, we provide design recommendations for interactive computer vision explanations, including carefully selected default views, independent input controls, and constrained output spaces.