Deep Joint Discriminative Feature Learning and Class-Aware Domain Alignment for Unsupervised Domain Adaptation

Deep learning techniques have been widely used to achieve promising results for fault diagnosis. In many real-world fault diagnosis applications, labeled training data (source domain) and unlabeled test data (target domain) have different distributions due to the frequent changes of working conditions, leading to performance degradation. This study proposes an end-to-end unsupervised domain adaptation bearing fault diagnosis model that combines domain alignment and discriminative feature learning on the basis of a 1D convolutional neural network. Joint training with classification loss, center-based discriminative loss, and correlation alignment loss between the two domains can adapt learned representations in the source domain for application to the target domain. Such joint training can also guarantee domain-invariant features with good intraclass compactness and interclass separability. Meanwhile, the extracted features can efficiently improve the cross-domain testing performance. Experimental results on the Case Western Reserve University bearing datasets confirm the superiority of the proposed method over many existing methods.

Download Full-text

Joint Domain Alignment and Discriminative Feature Learning for Unsupervised Deep Domain Adaptation

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v33i01.33013296 ◽

2019 ◽

Vol 33 ◽

pp. 3296-3303 ◽

Cited By ~ 23

Author(s):

Chao Chen ◽

Zhihong Chen ◽

Boyuan Jiang ◽

Xinyu Jin

Keyword(s):

Domain Adaptation ◽

Feature Learning ◽

Feature Space ◽

Feature Representation ◽

Learning Method ◽

Target Domain ◽

Shared Feature ◽

Class Separability ◽

Discriminative Feature ◽

Domain Alignment

Recently, considerable effort has been devoted to deep domain adaptation in computer vision and machine learning communities. However, most of existing work only concentrates on learning shared feature representation by minimizing the distribution discrepancy across different domains. Due to the fact that all the domain alignment approaches can only reduce, but not remove the domain shift, target domain samples distributed near the edge of the clusters, or far from their corresponding class centers are easily to be misclassified by the hyperplane learned from the source domain. To alleviate this issue, we propose to joint domain alignment and discriminative feature learning, which could benefit both domain alignment and final classification. Specifically, an instance-based discriminative feature learning method and a center-based discriminative feature learning method are proposed, both of which guarantee the domain invariant features with better intra-class compactness and inter-class separability. Extensive experiments show that learning the discriminative features in the shared feature space can significantly boost the performance of deep domain adaptation methods.

Download Full-text