Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2511.07974 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911259095465984 |
|---|---|
| author | Zhang, Lintong Yin, Kang Lee, Seong-Whan |
| author_facet | Zhang, Lintong Yin, Kang Lee, Seong-Whan |
| contents | Attribution-based explanation techniques capture key patterns to enhance visual interpretability; however, these patterns often lack the granularity needed for insight in fine-grained tasks, particularly in cases of model misclassification, where explanations may be insufficiently detailed. To address this limitation, we propose a fine-grained counterfactual explanation framework that generates both object-level and part-level interpretability, addressing two fundamental questions: (1) which fine-grained features contribute to model misclassification, and (2) where dominant local features influence counterfactual adjustments. Our approach yields explainable counterfactuals in a non-generative manner by quantifying similarity and weighting component contributions within regions of interest between correctly classified and misclassified samples. Furthermore, we introduce a saliency partition module grounded in Shapley value contributions, isolating features with region-specific relevance. Extensive experiments demonstrate the superiority of our approach in capturing more granular, intuitively meaningful regions, surpassing fine-grained methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_07974 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Towards Fine-Grained Interpretability: Counterfactual Explanations for Misclassification with Saliency Partition Zhang, Lintong Yin, Kang Lee, Seong-Whan Artificial Intelligence Attribution-based explanation techniques capture key patterns to enhance visual interpretability; however, these patterns often lack the granularity needed for insight in fine-grained tasks, particularly in cases of model misclassification, where explanations may be insufficiently detailed. To address this limitation, we propose a fine-grained counterfactual explanation framework that generates both object-level and part-level interpretability, addressing two fundamental questions: (1) which fine-grained features contribute to model misclassification, and (2) where dominant local features influence counterfactual adjustments. Our approach yields explainable counterfactuals in a non-generative manner by quantifying similarity and weighting component contributions within regions of interest between correctly classified and misclassified samples. Furthermore, we introduce a saliency partition module grounded in Shapley value contributions, isolating features with region-specific relevance. Extensive experiments demonstrate the superiority of our approach in capturing more granular, intuitively meaningful regions, surpassing fine-grained methods. |
| title | Towards Fine-Grained Interpretability: Counterfactual Explanations for Misclassification with Saliency Partition |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2511.07974 |