Multi-scale transfer voting mechanism
Domain adaption models are widely applied to fault transfer diagnosis. However, the traditional domain adaption models can output only one high-dimension transfer feature (TF), thus it is difficult to capture domain-invariant information. Besides, using only one fully-connected top classifier probably causes overfitting. Considering these two problems, we propose a Multi-Scale Transfer Voting Mechanism (MSTVM) to improve the classical domain adaption models, and it can be universally applicable to any one of most domain adaption models. MSTVM consists of two sub-strategies: Multi-Scale Transfer Mechanism (MSTM) and Multiple Transfer Voting Mechanism (MTVM). The MSTM block includes several branches with multi-scale convolutional and pooling operations, and it can output several multi-scale TFs to strengthen domain confusion. The MTVM block consists of multiple top classifiers and a plurality voting operation, thus MTVM can effectively avoid overfitting and improve generalization ability. MSTVM has the advantages of MSTM and MTVM. Via two transfer diagnosis experiments, the advantage of MSTVM for improving various domain adaption models is verified.
For the detail, please see: Yi Qin, Xin Wang, Quan Qian, Huayan Pu, Jun Luo. Multi-scale transfer voting mechanism: a new strategy for domain adaption. IEEE Transactions on Industrial Informatics, 2020, DOI 10.1109/TII.2020.3045392.