Attribute-based structural damage identification by few-shot meta learning with inter-class knowledge transfer

计算机科学 人工智能 机器学习 集合(抽象数据类型) 学习迁移 过程(计算) 特征向量 特征(语言学) 鉴定(生物学) 数据挖掘 班级(哲学) 模式识别(心理学) 语言学 哲学 植物 生物 程序设计语言 操作系统
作者
Yang Xu,Yuequan Bao,Yufeng Zhang,Hui Li
出处
期刊:Structural Health Monitoring-an International Journal [SAGE Publishing]
卷期号:20 (4): 1494-1517 被引量:57
标识
DOI:10.1177/1475921720921135
摘要

Image archives of multi-class structural damages can be collected by manual inspection and then used for structural damage identification. On one hand, conventional image-processing-based approaches rely on optimal designs of hand-crafted feature detectors and lack universal adaptability for various application cases; on the other hand, regular supervised learning techniques require complete damage types and sufficient training examples to establish a robust damage recognition model, which brings up a time-labor-consuming image collection process. To solve these problems, this study proposes a nested attribute-based few-shot meta learning paradigm for structural damage identification. First, an external few-shot meta learning module is established based on different classification tasks named as meta-batches to produce robust classifiers for new damage types, in which support and query subsets including partial damage types and a few examples are randomly sampled from the original image dataset. Second, an embedded internal attribute-based transfer learning model is trained by minimizing the l 2 -norm and angular losses of attribute representation vectors in an end-to-end manner, where damage attributes act as the common inter-class knowledge and are transferred from the source damage space of support set to the target damage space of query set. Finally, the proposed approach is validated on a real-world structural damage image dataset, which contains 1000 examples of 10 representative damage types in total. Results show the proposed approach produces an overall accuracy of 93.5% and an average area under the ROC curve of 0.96 for 10 damage types. The general equilibrium of average precision and recall indicates that the trained model is balanced to both positive and negative examples for each damage type. Compared with a regular supervised learning model by directly classifying input images with one-hot vector labels, the proposed approach generates higher accuracy and better robustness. Parameter study suggests the proposed paradigm enables to train a stable and reliable meta learning classification model that can perform well across a series of settings about the ratio between support and query subsets. Theoretical analysis is also performed to explain why meta learning surpasses regular supervised learning.

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
云弦发布了新的文献求助10
刚刚
1秒前
Kobe发布了新的文献求助10
1秒前
Lucas的应助被平常破茧采纳,获得10
1秒前
1秒前
awen完成签到,获得积分10
2秒前
2秒前
2秒前
zxz发布了新的文献求助10
2秒前
Slaimigo发布了新的文献求助10
3秒前
3秒前
Lucas的应助被小凯采纳,获得10
3秒前
高山的应助被调皮汽车采纳,获得50
3秒前
3秒前
3秒前
高天完成签到,获得积分10
3秒前
3秒前
3秒前
4秒前
领导范儿的应助被刘谋采纳,获得10
4秒前
4秒前
Juvenilesy的应助被sinmon采纳,获得10
4秒前
4秒前
我是老大的应助被jdmeme采纳,获得10
4秒前
4秒前
852的应助被午凌二采纳,获得10
4秒前
5秒前
guoleileity完成签到,获得积分10
5秒前
挚友发布了新的文献求助10
5秒前
秋风的应助被科研通管家采纳,获得20
5秒前
我是老大的应助被科研通管家采纳,获得10
5秒前
Marcia完成签到,获得积分10
5秒前
上官若男的应助被科研通管家采纳,获得10
5秒前
朱婷完成签到,获得积分10
5秒前
大模型的应助被科研通管家采纳,获得10
5秒前
null的应助被科研通管家采纳,获得10
5秒前
nn114发布了新的文献求助10
5秒前
bkagyin的应助被科研通管家采纳,获得10
6秒前
蓝天的应助被科研通管家采纳,获得10
6秒前
Criminology34的应助被科研通管家采纳,获得10
6秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1500
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
John McDowells Bildungstheorie 800
八旗制度の研究 600
Analyses de reconnaissances de dettes passées devant les échevins d'Ypres (1249-1291) 600
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8161857
求助须知:如何正确求助?哪些是违规求助? 9556272
关于积分的说明 21733778
捐赠科研通 7751772
什么是DOI,文献DOI怎么找? 3427616
关于科研通互助平台的介绍 2552632
邀请新用户注册赠送积分活动 2472079