MaskDiME: Adaptive Masked Diffusion for Precise and Efficient Visual Counterfactual Explanations
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908988748070912 |
|---|---|
| author | Guo, Changlu Christensen, Anders Nymark Dahl, Anders Bjorholm Hannemose, Morten Rieger |
| author_facet | Guo, Changlu Christensen, Anders Nymark Dahl, Anders Bjorholm Hannemose, Morten Rieger |
| contents | Visual counterfactual explanations aim to reveal the minimal semantic modifications that can alter a model's prediction, providing causal and interpretable insights into deep neural networks. However, existing diffusion-based counterfactual generation methods are often computationally expensive, slow to sample, and imprecise in localizing the modified regions. To address these limitations, we propose MaskDiME, a simple, fast, yet effective diffusion framework that unifies semantic consistency and spatial precision through localized sampling. Our approach adaptively focuses on decision-relevant regions to achieve localized and semantically consistent counterfactual generation while preserving high image fidelity. Our training-free framework, MaskDiME, performs inference over 30x faster than the baseline and achieves comparable or state-of-the-art performance across five benchmark datasets spanning diverse visual domains, establishing a practical and generalizable solution for efficient counterfactual explanation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_18792 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | MaskDiME: Adaptive Masked Diffusion for Precise and Efficient Visual Counterfactual Explanations Guo, Changlu Christensen, Anders Nymark Dahl, Anders Bjorholm Hannemose, Morten Rieger Computer Vision and Pattern Recognition Visual counterfactual explanations aim to reveal the minimal semantic modifications that can alter a model's prediction, providing causal and interpretable insights into deep neural networks. However, existing diffusion-based counterfactual generation methods are often computationally expensive, slow to sample, and imprecise in localizing the modified regions. To address these limitations, we propose MaskDiME, a simple, fast, yet effective diffusion framework that unifies semantic consistency and spatial precision through localized sampling. Our approach adaptively focuses on decision-relevant regions to achieve localized and semantically consistent counterfactual generation while preserving high image fidelity. Our training-free framework, MaskDiME, performs inference over 30x faster than the baseline and achieves comparable or state-of-the-art performance across five benchmark datasets spanning diverse visual domains, establishing a practical and generalizable solution for efficient counterfactual explanation. |
| title | MaskDiME: Adaptive Masked Diffusion for Precise and Efficient Visual Counterfactual Explanations |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.18792 |