ABSTRACT

As a data-driven method, the performance of deep convolutional neural networks (CNN) relies heavily on training data. The prediction results of traditional networks give a bias toward larger classes, which tend to be the background in the semantic segmentation task. This becomes a major problem for fault detection, where the targets appear very small on the images and vary in both types and sizes. In this paper we propose a new network architecture, DefectNet, that offers multiclass (including but not limited to) defect detection on highlyimbalanced datasets. DefectNet consists of two parallel paths, which are a fully convolutional network and a dilated convolutional network to detect large and small objects respectively. We propose a hybrid loss maximising the usefulness of a dice loss and a cross entropy loss, and we also employ the leaky rectified linear unit (ReLU) to deal with rare occurrence of some targets in training batches. The prediction results show that our DefectNet outperforms state-of-the-art networks for detecting multi-class defects with the average accuracy improvement of approximately 10% on a wind turbine.

摘要

一个样本驱使的方法，深度卷积神经网络的效果嫉妒依赖训练数据，传统网络的预测结果对于较大的类别具有偏置，在语义分割中的任务倾向于背景。对于故障检测这将变成一个主要的问题，在图像中的目标是非常小而且有不同的类型和尺寸。在这篇文章中我们采用了一个新的网络结构，缺陷网络，在极度不平衡的数据集上，它提供了多类别(包括但不限制的)缺陷检测。缺陷网络包含两个平行路径，一个是全卷积网络和一个空洞卷积网络分别去发现大和小目标。我们采用了一个混合损失最大化利用距离损失和交叉熵损失，同样我们也使用漏整流线型单元(LReLU)去解决在训练批次中少量出现的目标。这个预测结果显示我们的DefectNet表现出最好的网络，对于检测多类型的缺陷平均结果提升了10%在风车涡轮上。