Architectural Works of the Early Republic Period from an Artificial Intelligence Perspective

Abstract

This study presents a versatile approach integrating various neural network architectures with a focus on classifying architectural works. To address the lack of suitable datasets in the literature, a custom dataset has been created and made publicly available. The study aims to determine the most effective model, taking into account fine details in architectural styles. In this context, a comparative analysis has been conducted on four different convolutional neural network (CNN) architectures, including a baseline model trained from scratch and models using transfer learning methods with VGG, ResNet, and EfficientNet architectures. Through experiments, the EfficientNet architecture was fine-tuned, achieving an accuracy of %84.65 for 3 architects and %74.08 for 16 architects. Additionally, the two obtained models were used as feature extractors to visualize relationships among architects in a 2D space using t-SNE dimension reduction technique. These promising results indicate that these techniques can significantly contribute to architectural style analysis and serve as valuable tools for creating innovative designs through the use of generative artificial intelligence.