DoorDet: Semi-Automated Multi-Class Door Detection Dataset via Object Detection and Large Language Models

TL;DR

This paper introduces a semi-automated method combining object detection and large language models to efficiently create a multi-class door dataset from floor plans, reducing manual effort and improving dataset quality.

Contribution

The work presents a novel pipeline that integrates deep learning and LLMs with human oversight for efficient, high-quality dataset construction in complex indoor scene analysis.

Findings

Reduces annotation effort significantly

Produces a high-quality multi-class door dataset

Demonstrates effective combination of deep learning and LLMs

Abstract

Accurate detection and classification of diverse door types in floor plans drawings is critical for multiple applications, such as building compliance checking, and indoor scene understanding. Despite their importance, publicly available datasets specifically designed for fine-grained multi-class door detection remain scarce. In this work, we present a semi-automated pipeline that leverages a state-of-the-art object detector and a large language model (LLM) to construct a multi-class door detection dataset with minimal manual effort. Doors are first detected as a unified category using a deep object detection model. Next, an LLM classifies each detected instance based on its visual and contextual features. Finally, a human-in-the-loop stage ensures high-quality labels and bounding boxes. Our method significantly reduces annotation cost while producing a dataset suitable for benchmarking neural models in floor plan analysis. This work demonstrates the potential of combining deep learning and multimodal reasoning for efficient dataset construction in complex real-world domains.