SeNeDiF-OOD: Semantic Nested Dichotomy Fusion for Out-of-Distribution Detection Methodology in Open-World Classification. A Case Study on Monument Style Classification
This addresses the problem of reliable OOD detection for AI systems in open-world environments, such as architectural style recognition, but appears incremental as it builds on existing hierarchical and fusion concepts.
The paper tackles the challenge of detecting diverse out-of-distribution data in open-world AI by proposing SeNeDiF-OOD, a hierarchical fusion methodology, and demonstrates in a monument style classification case study that it significantly outperforms traditional baselines in filtering OOD categories while maintaining in-distribution performance.
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.