Interactivity x Explainability: Toward Understanding How Interactivity Can Improve Computer Vision Explanations

2025-04-14

AI Summary

Static visual explanations—such as heatmaps, concept-based attributions, and prototype-based methods—suffer from information overload, poor semantic-pixel alignment, and limited exploratory capability. This paper presents the first systematic investigation of interactive mechanisms across these three dominant computer vision explanation paradigms. Through a 24-participant user study on fine-grained bird recognition, we employ mixed qualitative and quantitative analysis to evaluate how dynamic masking, concept filtering, and prototype navigation impact information acquisition efficiency, alignment accuracy, and cognitive expansion. We derive three human-AI collaborative explanation design principles: adaptive default views, decoupled input controls, and constrained output spaces; identify novel challenges—including interaction overload and intent misalignment; and formulate seven actionable, implementation-ready guidelines for interactive explainable AI. This work has been accepted to CHI ’25.

Technology Category

• Computer Vision: Interpretability, Explainability, and Transparency
• Humans and AI: Explainable AI (XAI) for Human Understanding
• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Assisted, interactive, and conversational search

Abstract

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.

Problem

• Improving static computer vision explanations with interactivity
• Addressing information overload and exploration limits in explanations
• Designing interactive solutions for heatmap, concept, and prototype explanations

Innovation

• Interactivity enhances user control in explanations
• Default views and input controls improve usability
• Constrained output spaces address new challenges