inis 23(3): e2

Research Article

Attention ConvMixer Model and Application for Fish Species Classification

Download224 downloads
  • @ARTICLE{10.4108/eetinis.v10i3.3562,
        author={Thanh Viet Le and Hoang-Minh-Quang Le and Van Yem Vu and Thi-Thao Tran and Van-Truong Pham},
        title={Attention ConvMixer Model and Application for Fish Species Classification},
        journal={EAI Endorsed Transactions on Industrial Networks and Intelligent Systems},
        volume={10},
        number={3},
        publisher={EAI},
        journal_a={INIS},
        year={2023},
        month={9},
        keywords={Fish species classification, Attention ConvMixer, Priority Channel Attention, Priority Spatial Attention},
        doi={10.4108/eetinis.v10i3.3562}
    }
    
  • Thanh Viet Le
    Hoang-Minh-Quang Le
    Van Yem Vu
    Thi-Thao Tran
    Van-Truong Pham
    Year: 2023
    Attention ConvMixer Model and Application for Fish Species Classification
    INIS
    EAI
    DOI: 10.4108/eetinis.v10i3.3562
Thanh Viet Le1, Hoang-Minh-Quang Le1, Van Yem Vu1,*, Thi-Thao Tran1, Van-Truong Pham1
  • 1: Hanoi University of Science and Technology
*Contact email: yem.vuvan@hust.edu.vn

Abstract

Exploring the ocean has always been one of the foremost challenges for humankind, and fish classification is one of the crucial tasks in this endeavor. Manual fish classification methods, although accurate, consume significant time, money, and effort, while computer-based methods such as image processing and traditional machine learning often fall short of achieving high accuracy. Recently, deep convolutional neural networks have demonstrated their capability to ensure both time efficiency and accuracy in this task. However, deep convolutional networks typically have a large number of parameters, requiring substantial training time, and the convolutional operations lack attentional mechanisms. Therefore, in this paper, we propose the AttentionConvMixer neural network with Priority Channel Attention (PCA) and Priority Spatial Attention (PSA). The proposed approach exhibits good performance across all three fish classification datasets without introducing any additional parameters, thus demonstrating the effectiveness of our proposed method.