Few-shot learning for image-based bridge damage detection

Gao, Yan ORCID: https://orcid.org/0000-0001-5890-9717, Li, Haijiang ORCID: https://orcid.org/0000-0001-6326-8133 and Fu, Weiqi 2023. Few-shot learning for image-based bridge damage detection. Engineering Applications of Artificial Intelligence 126 (PartC) , 107078. 10.1016/j.engappai.2023.107078

Preview

PDF - Published Version Available under License Creative Commons Attribution Non-commercial No Derivatives. Download (7MB) | Preview

Abstract

Autonomous bridge visual inspection is a real-world challenge due to various materials, surface coatings, and changing light and weather conditions. Traditional supervised learning relies on massive annotated data to establish a robust model, which requires a time-consuming data acquisition process. This work proposes a few-shot learning (FSL) approach based on improved ProtoNet for damage detection with just a few labeled examples. Feature embedding is achieved through cross-domain transfer learning from ImageNet instead of episodic training. The ProtoNet is improved with embedding normalization to enhance transduction performance based on Euclidean distance and a linear classifier for classification. The approach is explored on a public dataset through different ablation experiments and achieves over 94% mean accuracy for 2-way 5-shot classification via the pre-trained GoogleNet after fine-tuning. Moreover, the proposed fine-tuning methods based on a fully connected layer (FCN) and Hadamard product are demonstrated with better performance than the previous method. Finally, the approach is validated using real bridge inspection images, demonstrating its capability of fast implementation for practical damage inspection with weakly supervised information.

Item Type:	Article
Date Type:	Publication
Status:	Published
Schools:	Engineering
Publisher:	Elsevier
ISSN:	0952-1976
Date of First Compliant Deposit:	6 September 2023
Date of Acceptance:	28 August 2023
Last Modified:	13 Sep 2023 23:40
URI:	https://orca.cardiff.ac.uk/id/eprint/162261

Actions (repository staff only)

Edit Item