期刊
AUTOMATION IN CONSTRUCTION
卷 143, 期 -, 页码 -出版社
ELSEVIER
DOI: 10.1016/j.autcon.2022.104544
关键词
Anomaly detection; Deep learning; Self -supervised learning; Transformer; A facial -recognition -like framework
资金
- National Natural Science Founda- tion of China [51708065]
This paper presents a novel method based on Transformer and self-supervised learning for pavement anomaly detection. Experimental results show that self-supervised learning improves performance and Transformer is applicable in this field. By building a facial recognition-like framework, performance can be enhanced without retraining.
Pavement anomaly detection can help reduce the pressure of data storage, transmission, labelling and processing. This paper describes a novel method based on transformer and self-supervised learning that assists in locating anomaly sections. Experimental results reveal that self-supervised learning can improve performance on a small dataset with unlabeled images. Transformer is proven to be applicable in the pavement distress detection field. The facial recognition-like framework we built can enhance the performance without training by putting new patches into the gallery. Removing similar patches does not affect the recognition results. The method is sufficiently efficient and miniaturized to support real-time work and can be applied directly to edge detection.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据