Fine-Grained Building Function Recognition from Street-View Images via Geometry-Aware Semi-Supervised Learning
This work addresses the problem of large-scale urban management by enabling efficient building function recognition with minimal annotation requirements, though it is incremental as it builds on existing semi-supervised methods.
The paper tackles fine-grained building function recognition from street-view images by proposing a geometry-aware semi-supervised framework that improves pseudo-label accuracy using geometric relationships, achieving performance gains of 7.6% over fully-supervised methods and 4.8% over state-of-the-art semi-supervised methods within the same categorization system.
In this work, we propose a geometry-aware semi-supervised framework for fine-grained building function recognition, utilizing geometric relationships among multi-source data to enhance pseudo-label accuracy in semi-supervised learning, broadening its applicability to various building function categorization systems. Firstly, we design an online semi-supervised pre-training stage, which facilitates the precise acquisition of building facade location information in street-view images. In the second stage, we propose a geometry-aware coarse annotation generation module. This module effectively combines GIS data and street-view data based on the geometric relationships, improving the accuracy of pseudo annotations. In the third stage, we combine the newly generated coarse annotations with the existing labeled dataset to achieve fine-grained functional recognition of buildings across multiple cities at a large scale. Extensive experiments demonstrate that our proposed framework exhibits superior performance in fine-grained functional recognition of buildings. Within the same categorization system, it achieves improvements of 7.6\% and 4.8\% compared to fully-supervised methods and state-of-the-art semi-supervised methods, respectively. Additionally, our method also performs well in cross-city scenarios, i.e., extending the model trained on OmniCity (New York) to new cities (i.e., Los Angeles and Boston) with different building function categorization systems. This study offers a new solution for large-scale multi-city applications with minimal annotation requirements, facilitating more efficient data updates and resource allocation in urban management.