TR2017-034

Deep Active Learning for Civil Infrastructure Defect Detection and Classification


    •  Feng, C., Liu, M.-Y., Kao, C.-C., Lee, T.-Y., "Deep Active Learning for Civil Infrastructure Defect Detection and Classification", International Workshop on Computing in Civil Engineering (IWCCE), June 2017.
      BibTeX TR2017-034 PDF
      • @inproceedings{Feng2017jun,
      • author = {Feng, Chen and Liu, Ming-Yu and Kao, Chieh-Chi and Lee, Teng-Yok},
      • title = {Deep Active Learning for Civil Infrastructure Defect Detection and Classification},
      • booktitle = {International Workshop on Computing in Civil Engineering (IWCCE)},
      • year = 2017,
      • month = jun,
      • url = {https://www.merl.com/publications/TR2017-034}
      • }
  • Research Areas:

    Artificial Intelligence, Computer Vision

Automatic detection and classification of defects in infrastructure surface images can largely boost its maintenance efficiency. Given enough labeled images, various supervised learning methods have been investigated for this task, including decision trees and support vector machines in previous studies, and deep neural networks more recently. However, in real world applications, labels are harder to obtain than images, due to the limited labeling resources (i.e., experts). Thus we propose a deep active learning system to maximize the performance. A deep residual network is firstly designed for defect detection and classification in an image. Following our active learning strategy, this network is trained as soon as an initial batch of labeled images becomes available. It is then used to select a most informative subset of new images and query labels from experts to retrain the network. Experiments demonstrate more efficient performance improvements of our method than baselines, achieving 87.5% detection accuracy.