# Local-to-Global Logical Explanations for Deep Vision Models Source: [Local-to-Global Logical Explanations for Deep Vision Models]() Collection index: [llms.txt]() Data updated: 2026-01-22T05:00:31.014Z Authors: Bhavan Vasu, Giuseppe Raffa, Prasad Tadepalli Published: 2026-01-19T21:21:58.000Z ## Abstract While deep neural networks are extremely effective at classifying images, they remain opaque and hard to interpret. We introduce local and global explanation methods for black-box models that generate explanations in terms of human-recognizable primitive concepts. Both the local explanations for a single image and the global explanations for a set of images are cast as logical formulas in monotone disjunctive-normal-form (MDNF), whose satisfaction guarantees that the model yields a high score on a given class. We also present an algorithm for explaining the classification of examples into multiple classes in the form of a monotone explanation list over primitive concepts. Despite their simplicity and interpretability we show that the explanations maintain high fidelity and coverage with respect to the blackbox models they seek to explain in challenging vision datasets. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Global Model Explanation on ADE20K (val)](): Global Model Explanation; ADE20K (val); Accuracy: 75.69. - [Global Model Explanation on Pascal-Parts (val)](): Global Model Explanation; Pascal-Parts (val); Accuracy: 53.49. ## Original sources and implementation [Original paper]() [PDF]()