Interactivity x Explainability: Toward Understanding How Interactivity Can Improve Computer Vision Explanations
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913794696937472 |
|---|---|
| author | Panigrahi, Indu Kim, Sunnie S. Y. Liaqat, Amna Jinturkar, Rohan Russakovsky, Olga Fong, Ruth Abtahi, Parastoo |
| author_facet | Panigrahi, Indu Kim, Sunnie S. Y. Liaqat, Amna Jinturkar, Rohan Russakovsky, Olga Fong, Ruth Abtahi, Parastoo |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_10745 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Interactivity x Explainability: Toward Understanding How Interactivity Can Improve Computer Vision Explanations Panigrahi, Indu Kim, Sunnie S. Y. Liaqat, Amna Jinturkar, Rohan Russakovsky, Olga Fong, Ruth Abtahi, Parastoo Human-Computer Interaction Computer Vision and Pattern Recognition 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. |
| title | Interactivity x Explainability: Toward Understanding How Interactivity Can Improve Computer Vision Explanations |
| topic | Human-Computer Interaction Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.10745 |