Local-to-Global Logical Explanations for Deep Vision Models

• URL: http://arxiv.org/abs/2601.13404v1
• Date: Mon, 19 Jan 2026 21:21:58 GMT
• Title: Local-to-Global Logical Explanations for Deep Vision Models
• Authors: Bhavan Vasu, Giuseppe Raffa, Prasad Tadepalli,
• Abstract summary: deep neural networks are effective at classifying images, but they remain opaque and hard to interpret.<n>We introduce local and global explanation methods for black-box models that generate explanations in terms of human-recognizable primitive concepts.<n>We show that the explanations maintain high fidelity and coverage with respect to the blackbox models they seek to explain in challenging vision datasets.
• Score: 8.433233101044197
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• 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.

Related papers

• Insight: Interpretable Semantic Hierarchies in Vision-Language Encoders [52.94006363830628]
  Language-aligned vision foundation models perform strongly across diverse downstream tasks.<n>Recent works decompose these representations into human-interpretable concepts, but provide poor spatial grounding and are limited to image classification tasks.<n>We propose Insight, a language-aligned concept foundation model that provides fine-grained concepts, which are human-interpretable and spatially grounded in the input image.
  arXiv  Detail & Related papers  (2026-01-20T09:57:26Z)
• FaCT: Faithful Concept Traces for Explaining Neural Network Decisions [56.796533084868884]
  Deep networks have shown remarkable performance across a wide range of tasks, yet getting a global concept-level understanding of how they function remains a key challenge.<n>We put emphasis on the faithfulness of concept-based explanations and propose a new model with model-inherent mechanistic concept-explanations.<n>Our concepts are shared across classes and, from any layer, their contribution to the logit and their input-visualization can be faithfully traced.
  arXiv  Detail & Related papers  (2025-10-29T13:35:46Z)
• Generating Part-Based Global Explanations Via Correspondence [8.83354835766461]
  We propose an approach that leverages user-defined part labels from a limited set of images and efficiently transfers them to a larger dataset.<n>This enables the generation of global symbolic explanations by aggregating part-based local explanations, ultimately providing human-understandable explanations for model decisions on a large scale.
  arXiv  Detail & Related papers  (2025-09-18T20:00:49Z)
• ConLUX: Concept-Based Local Unified Explanations [14.110188927768736]
  toolname is a general framework to provide concept-based local explanations for any machine learning models. We have instantiated toolname on four different types of explanation techniques: LIME, Kernel SHAP, Anchor, and LORE. Our evaluation results demonstrate that toolname offers more faithful explanations and makes them more understandable to users.
  arXiv  Detail & Related papers  (2024-10-16T10:34:11Z)
• Explainability for Large Language Models: A Survey [59.67574757137078]
  Large language models (LLMs) have demonstrated impressive capabilities in natural language processing. This paper introduces a taxonomy of explainability techniques and provides a structured overview of methods for explaining Transformer-based language models.
  arXiv  Detail & Related papers  (2023-09-02T22:14:26Z)
• Interpreting Vision and Language Generative Models with Semantic Visual Priors [3.3772986620114374]
  We develop a framework based on SHAP that allows for generating meaningful explanations leveraging the meaning representation of the output sequence as a whole. We demonstrate that our method generates semantically more expressive explanations than traditional methods at a lower compute cost.
  arXiv  Detail & Related papers  (2023-04-28T17:10:08Z)
• Learning with Explanation Constraints [91.23736536228485]
  We provide a learning theoretic framework to analyze how explanations can improve the learning of our models. We demonstrate the benefits of our approach over a large array of synthetic and real-world experiments.
  arXiv  Detail & Related papers  (2023-03-25T15:06:47Z)
• Human-Centered Concept Explanations for Neural Networks [47.71169918421306]
  We introduce concept explanations including the class of Concept Activation Vectors (CAV) We then discuss approaches to automatically extract concepts, and approaches to address some of their caveats. Finally, we discuss some case studies that showcase the utility of such concept-based explanations in synthetic settings and real world applications.
  arXiv  Detail & Related papers  (2022-02-25T01:27:31Z)
• Global explainability in aligned image modalities [0.0]
  We focus on image modalities that are naturally aligned such that each pixel position represents a similar relative position on the imaged object. We propose the pixel-wise aggregation of image-wise explanations as a simple method to obtain label-wise and overall global explanations. We then apply these methods to ultra-widefield retinal images, a naturally aligned modality.
  arXiv  Detail & Related papers  (2021-12-17T16:05:11Z)
• MACE: Model Agnostic Concept Extractor for Explaining Image Classification Networks [10.06397994266945]
  We propose MACE: a Model Agnostic Concept Extractor, which can explain the working of a convolutional network through smaller concepts. We validate our framework using VGG16 and ResNet50 CNN architectures, and on datasets like Animals With Attributes 2 (AWA2) and Places365.
  arXiv  Detail & Related papers  (2020-11-03T04:40:49Z)
• The Struggles of Feature-Based Explanations: Shapley Values vs. Minimal Sufficient Subsets [61.66584140190247]
  We show that feature-based explanations pose problems even for explaining trivial models. We show that two popular classes of explainers, Shapley explainers and minimal sufficient subsets explainers, target fundamentally different types of ground-truth explanations.
  arXiv  Detail & Related papers  (2020-09-23T09:45:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.