Artificial Intelligence and Data Science
Online ISSN : 2435-9262
Construction of a feature space for retrieval and attribute recognition via contrastive learning using bridge inspection images and damage reports
Tatsuki SEINO, Keisuke MAEDA, Naoki SAITO, Takahiro OGAWA, Miki HASEYAMA
Author information
JOURNAL OPEN ACCESS

2026 Volume 7 Issue 3 Pages 768-784

Details
Abstract

This study investigates a method for constructing a feature space for retrieval and attribute recognition through contrastive learning using bridge inspection images and damage reports. Although Contrastive Language-Image Pre-training (CLIP) has demonstrated strong performance on general image-text pairs, its feature space is not necessarily well suited to specialized domains such as bridge inspection. To address this issue, we fine-tune a pretrained CLIP model using approximately 130,000 bridge inspection image–damage report pairs and construct a feature space specialized for bridge inspection. In the experiments, we evaluate retrieval performance and examine attribute recognition performance in terms of structural component type, damage type, condition rating, and maintenance action category. Experimental results show that the proposed method achieves better retrieval performance than the pretrained CLIP model and is also effective for recognizing attributes related to bridge inspection.

Content from these authors
© 2026 Japan Society of Civil Engineers
Previous article Next article
feedback
Top