\textit{FocaLogic}: Logic-Based Interpretation of Visual Model Decisions
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915736966922240 |
|---|---|
| author | Zhao, Chenchen Chen, Muxi Xu, Qiang |
| author_facet | Zhao, Chenchen Chen, Muxi Xu, Qiang |
| contents | Interpretability of modern visual models is crucial, particularly in high-stakes applications. However, existing interpretability methods typically suffer from either reliance on white-box model access or insufficient quantitative rigor. To address these limitations, we introduce FocaLogic, a novel model-agnostic framework designed to interpret and quantify visual model decision-making through logic-based representations. FocaLogic identifies minimal interpretable subsets of visual regions-termed visual focuses-that decisively influence model predictions. It translates these visual focuses into precise and compact logical expressions, enabling transparent and structured interpretations. Additionally, we propose a suite of quantitative metrics, including focus precision, recall, and divergence, to objectively evaluate model behavior across diverse scenarios. Empirical analyses demonstrate FocaLogic's capability to uncover critical insights such as training-induced concentration, increasing focus accuracy through generalization, and anomalous focuses under biases and adversarial attacks. Overall, FocaLogic provides a systematic, scalable, and quantitative solution for interpreting visual models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_12049 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | \textit{FocaLogic}: Logic-Based Interpretation of Visual Model Decisions Zhao, Chenchen Chen, Muxi Xu, Qiang Computer Vision and Pattern Recognition Artificial Intelligence Interpretability of modern visual models is crucial, particularly in high-stakes applications. However, existing interpretability methods typically suffer from either reliance on white-box model access or insufficient quantitative rigor. To address these limitations, we introduce FocaLogic, a novel model-agnostic framework designed to interpret and quantify visual model decision-making through logic-based representations. FocaLogic identifies minimal interpretable subsets of visual regions-termed visual focuses-that decisively influence model predictions. It translates these visual focuses into precise and compact logical expressions, enabling transparent and structured interpretations. Additionally, we propose a suite of quantitative metrics, including focus precision, recall, and divergence, to objectively evaluate model behavior across diverse scenarios. Empirical analyses demonstrate FocaLogic's capability to uncover critical insights such as training-induced concentration, increasing focus accuracy through generalization, and anomalous focuses under biases and adversarial attacks. Overall, FocaLogic provides a systematic, scalable, and quantitative solution for interpreting visual models. |
| title | \textit{FocaLogic}: Logic-Based Interpretation of Visual Model Decisions |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2601.12049 |