4.7 Article

Few-shot learning for image-based bridge damage detection

Journal

Publisher

PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.engappai.2023.107078

Keywords

Few-shot learning; Damage detection; Cross-domain transfer learning; Prototypical networks; Transduction

Ask authors/readers for more resources

This study proposes a few-shot learning approach for damage detection using cross-domain transfer learning and improved ProtoNet. The experiments show that the method achieves high accuracy on a public dataset and demonstrates its capability in practical applications.
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 fewshot 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.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.7
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available