Visual Model Checking: Graph-Based Inference of Visual Routines for Image Retrieval

2026-02-19

AI Summary

Existing image retrieval methods struggle to reliably handle natural language queries involving complex relationships, object compositions, or precise constraints such as identity, count, or spatial proportions. This work proposes the first verifiable image retrieval framework that integrates formal verification with graph-based reasoning and neural code generation. By introducing a graph-based verification mechanism, the approach explicitly validates atomic conditions derived from the query and combines embedding-based retrieval models with a formal reasoning system to produce transparently annotated results and interpretable feedback. The method significantly enhances both accuracy and trustworthiness over mainstream embedding-based retrieval systems while enabling fine-grained constraint satisfaction verification under open-vocabulary queries.

Technology Category

• Computer Vision: Image and Video Retrieval
• Knowledge Representation and Reasoning: Qualitative Reasoning
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Graph Algorithms and Modeling for the Web: Querying, indexing, and retrieval in Web-related graphs
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Information retrieval lies at the foundation of the modern digital industry. While natural language search has seen dramatic progress in recent years largely driven by embedding-based models and large-scale pretraining, the field still faces significant challenges. Specifically, queries that involve complex relationships, object compositions, or precise constraints such as identities, counts and proportions often remain unresolved or unreliable within current frameworks. In this paper, we propose a novel framework that integrates formal verification into deep learning-based image retrieval through a synergistic combination of graph-based verification methods and neural code generation. Our approach aims to support open-vocabulary natural language queries while producing results that are both trustworthy and verifiable. By grounding retrieval results in a system of formal reasoning, we move beyond the ambiguity and approximation that often characterize vector representations. Instead of accepting uncertainty as a given, our framework explicitly verifies each atomic truth in the user query against the retrieved content. This allows us to not only return matching results, but also to identify and mark which specific constraints are satisfied and which remain unmet, thereby offering a more transparent and accountable retrieval process while boosting the results of the most popular embedding-based approaches.

Problem

• image retrieval
• natural language queries
• complex relationships
• formal verification
• embedding-based models

Innovation

• visual model checking
• graph-based inference
• formal verification
• neural code generation
• verifiable image retrieval