Zero-shot Building Age Classification from Facade Image Using GPT-4

TL;DR

This paper explores using GPT-4 Vision in a zero-shot manner to classify building ages from facade images, demonstrating potential without training but with limitations in accuracy and granularity.

Contribution

It introduces a novel zero-shot classification approach using GPT-4 Vision prompts for building age estimation from facade images.

Findings

Achieved 39.69% accuracy in classifying building age epochs.

Mean absolute error of 0.85 decades indicates successful rough predictions.

Struggles with very old buildings and fine-grained age distinctions within 2 decades.

Abstract

A building's age of construction is crucial for supporting many geospatial applications. Much current research focuses on estimating building age from facade images using deep learning. However, building an accurate deep learning model requires a considerable amount of labelled training data, and the trained models often have geographical constraints. Recently, large pre-trained vision language models (VLMs) such as GPT-4 Vision, which demonstrate significant generalisation capabilities, have emerged as potential training-free tools for dealing with specific vision tasks, but their applicability and reliability for building information remain unexplored. In this study, a zero-shot building age classifier for facade images is developed using prompts that include logical instructions. Taking London as a test case, we introduce a new dataset, FI-London, comprising facade images and building age epochs. Although the training-free classifier achieved a modest accuracy of 39.69%, the mean absolute error of 0.85 decades indicates that the model can predict building age epochs successfully albeit with a small bias. The ensuing discussion reveals that the classifier struggles to predict the age of very old buildings and is challenged by fine-grained predictions within 2 decades. Overall, the classifier utilising GPT-4 Vision is capable of predicting the rough age epoch of a building from a single facade image without any training.