Meta-learning Convolutional Neural Architectures for Multi-target Concrete Defect Classification with the COncrete DEfect BRidge IMage Dataset

被引:95
作者
Mundt, Martin [1 ]
Majumder, Sagnik [1 ]
Murali, Sreenivas [1 ]
Panetsos, Panagiotis [2 ]
Ramesh, Visvanathan [1 ]
机构
[1] Goethe Univ, Frankfurt, Germany
[2] Egnatia Odos AE, Thessaloniki, Greece
来源
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019) | 2019年
基金
欧盟地平线“2020”;
关键词
NETWORKS; TEXTURE;
D O I
10.1109/CVPR.2019.01145
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Recognition of defects in concrete infrastructure, especially in bridges, is a costly and time consuming crucial first step in the assessment of the structural integrity. Large variation in appearance of the concrete material, changing illumination and weather conditions, a variety of possible surface markings as well as the possibility for different types of defects to overlap, make it a challenging real-world task. In this work we introduce the novel COncrete DEfect BRidge IMage dataset (CODEBRIM) for multi-target classification of five commonly appearing concrete defects. We investigate and compare two reinforcement learning based meta-learning approaches, MetaQNN and efficient neural architecture search, to find suitable convolutional neural network architectures for this challenging multi-class multi-target task. We show that learned architectures have fewer overall parameters in addition to yielding better multi-target accuracy in comparison to popular neural architectures from the literature evaluated in the context of our application.
引用
收藏
页码:11188 / 11197
页数:10
相关论文
共 38 条
  • [1] Using filter banks in Convolutional Neural Networks for texture classification
    Andrearczyk, Vincent
    Whelan, Paulf.
    [J]. PATTERN RECOGNITION LETTERS, 2016, 84 : 63 - 69
  • [2] [Anonymous], EUR C COMP VIS ECCV
  • [3] [Anonymous], 2005, ICCV
  • [4] [Anonymous], 2017, IRONMAK STEELMAK
  • [5] Baker B., 2017, INT C LEARNING REPRE
  • [6] Bell S, 2015, PROC CVPR IEEE, P3479, DOI 10.1109/CVPR.2015.7298970
  • [7] Cai Han, 2018, AAAI C ART INT AAAI
  • [8] CHOLLET F, 2017, PROC CVPR IEEE, P1800, DOI DOI 10.1109/CVPR.2017.195
  • [9] Cimpoi M., 2015, COMPUTER VISION PATT
  • [10] da Silva Wilson R. L., 2018, INT C EXP MECH ICEM1