# Vocabulary Aligned Explanations for Computer Vision Models

DevFeed: [Vocabulary Aligned Explanations for Computer Vision Models](<https://devfeed.tech/articles/vocabulary-aligned-explanations-for-computer-vision-models-115161.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.01391>)

Author: Erfan Mirhaji, Nikhil Krishnaswamy, Jill Zarestky, Lisa Mason, Nathaniel Blanchard, Sarath Sreedharan

Published: 2026-11-03T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Computer vision](<https://devfeed.tech/topics/computer-vision.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [image recognition](<https://devfeed.tech/topics/image-recognition.md>)

Tags: [computer-vision](<https://devfeed.tech/tags/computer-vision.md>), [concepts](<https://devfeed.tech/tags/concepts.md>), [confidence](<https://devfeed.tech/tags/confidence.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [fluent](<https://devfeed.tech/tags/fluent.md>), [framework](<https://devfeed.tech/tags/framework.md>), [highlights](<https://devfeed.tech/tags/highlights.md>), [knowledge](<https://devfeed.tech/tags/knowledge.md>), [models](<https://devfeed.tech/tags/models.md>), [rules](<https://devfeed.tech/tags/rules.md>)

## AI overview

FLUENT explains image classifications with expert-authored logical rules built from domain-specific concepts, including concepts that must be present, alternatives, and absences. The post-hoc framework combines predicted labels and concept states with empirically estimated likelihoods and concept priors to score rules over satisfying concept assignments, then normalizes scores as relative confidence among candidate explanations. It illustrates the selected rule with occlusion highlights for positive concepts in the query image and localized examples from retrieved reference images for absent concepts, aiming to help users recognize the named concepts. The supplied text describes the framework's approach but provides no evaluation results.

## Source excerpt

arXiv:2611.01391v1 Announce Type: cross Abstract: Optimizing vision models for accuracy does not force the model to learn and utilize human-understandable and domain-specific concepts and rules. We propose explaining image classifications through domain-specific concepts, visual evidence, and expert knowledge expressed as logical rules. We introduce FLUENT (Framework for Localized, Uncertainty-Aware Explanations in Normative Terminology), a post-hoc framework that ranks expert-authored rules combining jointly required, alternative, and absent concepts. To account for prediction errors, FLUENT combines predicted labels and concept states with empirically estimated likelihoods and concept priors. It scores each rule by calculating support over satisfying assignments to the concepts mentioned in that rule, then normalizes these scores to express relative confidence among candidate explanations. The selected rule is illustrated through occlusion-based highlights for positive concept mentions in the query image and localized examples in retrieved reference images for negative mentions. These illustrations are intended to show end users unfamiliar with the domain what the concepts named in an explanation look like. FLUENT combines domain knowledge and model accuracy, and delivers visual concept highlights and explicit rule confidence to explain an image in the vocabulary of an application domain.