.png){kind=icon}
.png){kind=icon}
Return
DiffExplainer: Towards cross-modal global explanations with diffusion models
.png){kind=icon}
OA
AI
DOI：10.1016/j.cviu.2025.104559.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Leverages diffusion models to generate images explaining classifier decisions. • Enables bias and spurious feature detection without manual intervention. • Outperforms activation maximization methods in image quality and feature analysis. • Enables specific model analysis by the use of fixed prompts.
Keywords:
Activation maximization
Explainability
Diffusion models
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
3.5
Papers:
428
Citations:
7.3K