CycleGAN based confusion model for cross-species plant disease image migration

被引:0
|
作者
Cui, Xiaohui [1 ]
Ying, Yongzhi [1 ]
Chen, Zhibo [1 ]
机构
[1] Beijing Forestry Univ, Sch Informat Sci & Technol, Engn Res Ctr Forestry Oriented Intelligent Inform, Natl Forestry & Grassland Adm, Beijing, Peoples R China
基金
中国国家自然科学基金;
关键词
Deep learning; generative adversarial nets; CycleGAN; image translation; SYSTEM;
D O I
10.3233/JIFS-210585
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The identification and classification of plant diseases is of great significance to ecological protection and deep learning methods have made a great of progress in the common plant diseases identification for specific plant. While faced with the same plant disease of other plants, due to the insufficient or low quality training data, current deep learning methods will be difficult to identify the diseases effectively and accurately. Inspired by the advantages of GAN in dataset expansion, we propose the CycleGAN based confusion model in this paper. In this paper, GAN framework is improved by adding noise label and learn together during training stage, which migrates the data of common plant diseases to the plants with insufficient or low quality data. In order to evaluate the quality of the migrated training dataset among different GAN approaches, we introduce the quality indicators of the migration images such as MMD, FID, EMD etc. We compare our model with other GANs model, and the experimental results show that the proposed model obtains better results in the migration process, which make it more effective for the identification of cross species plant diseases.
引用
收藏
页码:6685 / 6696
页数:12
相关论文
共 50 条
  • [31] Cross-species translocation of mRNA from host plants into the parasitic plant dodder
    Roney, Jeannine K.
    Khatibi, Piyum A.
    Westwood, James H.
    [J]. PLANT PHYSIOLOGY, 2007, 143 (02) : 1037 - 1043
  • [32] Cross-species mutation assay based on the Pig-a gene
    Raja, Sarojini
    [J]. MUTAGENESIS, 2009, 24 (06) : 532 - 532
  • [33] Computational identification of disease models through cross-species phenotype comparison
    Cacheiro, Pilar
    Pava, Diego
    Parkinson, Helen
    VanZanten, Maya
    Wilson, Robert
    Gunes, Osman
    [J]. DISEASE MODELS & MECHANISMS, 2024, 17 (06)
  • [34] Understanding skeletal disease with cross-species transcriptomics meta-analysis
    Soul, J.
    Hardingham, T.
    Boot-Handford, R.
    Schwartz, J. -M.
    [J]. INTERNATIONAL JOURNAL OF EXPERIMENTAL PATHOLOGY, 2018, 99 (06) : A55 - A55
  • [35] Heterologous cross-seeding mimics cross-species prion conversion in a yeast model
    Vishveshwara, Namitha
    Liebman, Susan W.
    [J]. BMC BIOLOGY, 2009, 7 : 26
  • [36] GeneWeaver: data driven alignment of cross-species genomics in biology and disease
    Baker, Erich
    Bubier, Jason A.
    Reynolds, Timothy
    Langston, Michael A.
    Chesler, Elissa J.
    [J]. NUCLEIC ACIDS RESEARCH, 2016, 44 (D1) : D555 - D559
  • [37] Heterologous cross-seeding mimics cross-species prion conversion in a yeast model
    Namitha Vishveshwara
    Susan W Liebman
    [J]. BMC Biology, 7
  • [38] CROSS-SPECIES GENOMICS MATCHES MUTATIONS AND CELL COMPARTMENTS TO MODEL EPENDYMOMA
    Wright, K. D.
    Johnson, R.
    Poppleton, H.
    Mohankumar, K. M.
    Finkelstein, D.
    Rand, V.
    Leary, S.
    White, E.
    Pounds, S.
    Northcott, P.
    Mack, S.
    Neale, G.
    Coyle, B.
    Atkinson, J.
    Dewire, M.
    Kranenburg, T. A.
    Gillespie, Y.
    Allen, J.
    Merchant, T.
    Hoop, F. A.
    Gajjar, A.
    Ellison, D. W.
    Taylor, M. D.
    Grundy, R. G.
    Gilbertson, R. J.
    [J]. NEURO-ONCOLOGY, 2010, 12 (06) : II25 - II25
  • [39] Depth image conversion model based on CycleGAN for growing tomato truss identification
    Jung, Dae-Hyun
    Kim, Cheoul Young
    Lee, Taek Sung
    Park, Soo Hyun
    [J]. PLANT METHODS, 2022, 18 (01)
  • [40] Toward a plant genomics initiative: Thoughts on the value of cross-species and cross-genera comparisons in the grasses
    McCouch, S
    [J]. PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA, 1998, 95 (05) : 1983 - 1985