Scholarlink

This paper introduces a hierarchical approach utilizing nested dichotomies to enhance the MonuMAI framework designed for architectural image classification. The study focuses on developing a foundational layer dedicated to distinguishing between building and non-building images, effectively reducing complexity by filtering out irrelevant data early in the classification process. Through empirical investigation utilizing a fine-tuned EfficientNet model, the study demonstrates substantial progress in handling out-of-distribution scenarios in monument detection. The model effectively filters out irrelevant images while accurately retaining most monument images, establishing a robust foundation for subsequent layers aimed at improving out-of-distribution detection, and recognizing new architectural styles post-deployment. This study specifically emphasizes the initial layer of our innovative system, setting the stage for future expansion and development of subsequent layers. This research marks a significant stride in mitigating OOD challenges within architectural image classification, highlighting the potential of hierarchical methodologies to propel MonuMAI and analogous systems towards more precise and adaptable AI solutions.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Establishing the Foundation for Out-of-Distribution Detection in Monument Classification Through Nested Dichotomies

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Ignacio Antequera-Sánchez,
  • Juan Luis Suárez-Díaz,
  • Rosana Montes,
  • Francisco Herrera

摘要

This paper introduces a hierarchical approach utilizing nested dichotomies to enhance the MonuMAI framework designed for architectural image classification. The study focuses on developing a foundational layer dedicated to distinguishing between building and non-building images, effectively reducing complexity by filtering out irrelevant data early in the classification process. Through empirical investigation utilizing a fine-tuned EfficientNet model, the study demonstrates substantial progress in handling out-of-distribution scenarios in monument detection. The model effectively filters out irrelevant images while accurately retaining most monument images, establishing a robust foundation for subsequent layers aimed at improving out-of-distribution detection, and recognizing new architectural styles post-deployment. This study specifically emphasizes the initial layer of our innovative system, setting the stage for future expansion and development of subsequent layers. This research marks a significant stride in mitigating OOD challenges within architectural image classification, highlighting the potential of hierarchical methodologies to propel MonuMAI and analogous systems towards more precise and adaptable AI solutions.