• Spectroscopy and Spectral Analysis
  • Vol. 41, Issue 7, 2171 (2021)
Jiang-sheng GUI1、*, Jing-yi FEI1、1;, and Xia-ping FU2、2;
Author Affiliations
  • 11. School of Information Science and Technology, Zhejiang Sci-Tech University, Hangzhou 310018, China
  • 22. Faculty of Mechanical Engineering & Automation, Zhejiang Sci-Tech University, Hangzhou 310018, China
  • show less
    DOI: 10.3964/j.issn.1000-0593(2021)07-2171-04 Cite this Article
    Jiang-sheng GUI, Jing-yi FEI, Xia-ping FU. Hyperspectral Imaging for Detection of Leguminivora Glycinivorella Based on 3D Few-Shot Meta-Learning Model[J]. Spectroscopy and Spectral Analysis, 2021, 41(7): 2171 Copy Citation Text show less
    Hyperspectral imaging system
    Fig. 1. Hyperspectral imaging system
    Structure of the 3D-Relation Network
    Fig. 2. Structure of the 3D-Relation Network
    Hyperspectral images of soybean samples(a): Normal soybean; (b): Soybean with egg;(c): Soybean with larvae; (d): Gnawed soybean
    Fig. 3. Hyperspectral images of soybean samples
    (a): Normal soybean; (b): Soybean with egg;(c): Soybean with larvae; (d): Gnawed soybean
    小样本
    学习模型
    特征提取
    模型
    学习率正确率/%
    1-shot5-shot
    MAMLResNet180.0150.98±1.1959.94±0.56
    0.00143.43±0.5548.03±0.23
    Conv40.0142.15±0.3852.65±0.79
    0.00135.15±0.7337.06±0.58
    MMResNet180.0169.19±1.2178.65±0.79
    0.00156.58±0.4769.49±0.82
    Conv40.0152.46±0.4064.09±0.70
    0.00148.07±0.9760.21±1.15
    3D-RNResNet180.0171.12±0.6182.75±2.50
    0.00165.90±0.7776.40±1.23
    Conv40.0157.31±0.9869.12±0.31
    0.00153.33±0.9665.15±1.17
    Table 1. Detection results of different classification models in the cases of 4-way 1-shot and 4-way 5-shot
    Jiang-sheng GUI, Jing-yi FEI, Xia-ping FU. Hyperspectral Imaging for Detection of Leguminivora Glycinivorella Based on 3D Few-Shot Meta-Learning Model[J]. Spectroscopy and Spectral Analysis, 2021, 41(7): 2171
    Download Citation