sis 18: e36

Research Article

Multichannel attention mechanisms fusion based on gate recurrent unit memory network for fine-grained image classification

Download425 downloads
  • @ARTICLE{10.4108/eai.27-1-2022.173165,
        author={Rui Yang and Dahai Li},
        title={Multichannel attention mechanisms fusion based on gate recurrent unit memory network for fine-grained image classification},
        journal={EAI Endorsed Transactions on Scalable Information Systems: Online First},
        volume={},
        number={},
        publisher={EAI},
        journal_a={SIS},
        year={2022},
        month={1},
        keywords={Multichannel attention mechanism, result fusion, fine-grained image classification, gate recurrent unit memory network},
        doi={10.4108/eai.27-1-2022.173165}
    }
    
  • Rui Yang
    Dahai Li
    Year: 2022
    Multichannel attention mechanisms fusion based on gate recurrent unit memory network for fine-grained image classification
    SIS
    EAI
    DOI: 10.4108/eai.27-1-2022.173165
Rui Yang1,2,*, Dahai Li1,2
  • 1: School of Electrical Engineering, Zhengzhou University of Science and Technology, Zhengzhou, 450015 China
  • 2: Henan Intelligent Information Processing and Control Engineering Technology Research Center, Zhengzhou, 450015 China
*Contact email: 352720214@qq.com

Abstract

This article has been retracted, and the retraction notice can be found here: http://dx.doi.org/10.4108/eai.8-4-2022.173792. Attention mechanism is widely used in fine-grained image classification. Most of the existing methods are to construct an attention weight map for simple weighted processing of features, but there are problems of low efficiency and slow convergence. Therefore, this paper proposes a multi-channel attention fusion mechanism based on the deep neural network model which can be trained end-to-end. Firstly, the different regions corresponding to the object are described by the attention diagram. Then the corresponding higher order statistical characteristics are extracted to obtain the corresponding representation. In many standard fine-grained image classification test tasks, the proposed method works best compared with other methods.