SeNeDiF-OOD: Semantic Nested Dichotomy Fusion for Out-of-Distribution Detection Methodology in Open-World Classification. A Case Study on Monument Style Classification

2026-01-26

AI Summary

This work addresses the challenge that heterogeneous out-of-distribution (OOD) data—encompassing low-level corruptions, semantic shifts, unknown classes, and adversarial examples—cannot be effectively detected by a single OOD detector in open-world classification. To this end, the authors propose a hierarchical OOD detection framework based on semantically nested binary fusion. The method employs multiple binary fusion nodes across abstraction levels to progressively integrate decision boundaries from different semantic granularities, decomposing OOD detection into a series of semantically aligned binary decisions. This unified approach effectively handles diverse OOD types, ranging from pixel-level anomalies to high-level semantic deviations. End-to-end experiments on the MonuMAI architectural style recognition system demonstrate that the proposed framework significantly outperforms existing OOD detection baselines in complex open-world scenarios while maintaining strong in-distribution classification performance.

Technology Category

• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Computer Vision: Object Detection & Categorization

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Out-of-distribution (OOD) detection is a fundamental requirement for the reliable deployment of artificial intelligence applications in open-world environments. However, addressing the heterogeneous nature of OOD data, ranging from low-level corruption to semantic shifts, remains a complex challenge that single-stage detectors often fail to resolve. To address this issue, we propose SeNeDiF-OOD, a novel methodology based on Semantic Nested Dichotomy Fusion. This framework decomposes the detection task into a hierarchical structure of binary fusion nodes, where each layer is designed to integrate decision boundaries aligned with specific levels of semantic abstraction. To validate the proposed framework, we present a comprehensive case study using MonuMAI, a real-world architectural style recognition system exposed to an open environment. This application faces a diverse range of inputs, including non-monument images, unknown architectural styles, and adversarial attacks, making it an ideal testbed for our proposal. Through extensive experimental evaluation in this domain, results demonstrate that our hierarchical fusion methodology significantly outperforms traditional baselines, effectively filtering these diverse OOD categories while preserving in-distribution performance.

Problem

• Out-of-Distribution Detection
• Open-World Classification
• Semantic Shift
• Heterogeneous OOD Data
• Monument Style Classification

Innovation

• Semantic Nested Dichotomy Fusion
• Out-of-Distribution Detection
• Open-World Classification
• Hierarchical Decision Fusion
• Monument Style Recognition