Zero- and few-shot learning for diseases recognition of Citrus aurantium L. using conditional adversarial autoencoders

Abstract Plant diseases can cause significant production and economic losses, and also seriously restrict the sustainable development of agriculture. Traditional plant diseases recognition method is time-consuming and highly dependent on expert experience. Therefore, most of the existing works design models based on deep learning to automatic recognition. However, they are sample-intensive and hard for the diagnosis of some Citrus aurantium L. diseases with only a few or even zero labeled samples for training. In this paper, we propose a novel generative model for zero- and few-shot recognition of Citrus aurantium L. diseases using conditional adversarial autoencoders (CAAE). CAAE learns to synthesize visual features so that the zero- and few-shot recognition can be transformed to a conventional supervised classification problem. Specifically, CAAE consists of encoder, decoder, and discriminator. Different from conditional variational autoencoder (CVAE), we impose a discriminator to train the encoder by adversarially minimizing the loss between the prior distribution and the encoding distribution. Our model achieves a harmonic mean accuracy of 53.4% for zero-shot recognition of Citrus aurantium L. diseases, which is 50.4% higher than CVAE. Extensive experiments carried out on public zero-shot benchmark datasets and a further case study on our own collected dataset of Citrus aurantium L. diseases demonstrate that our model is suitable for the application of zero- and few-shot Citrus aurantium L. diseases diagnosis.

[1]  Philip S. Yu,et al.  Generative Dual Adversarial Network for Generalized Zero-Shot Learning , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Soma Biswas,et al.  Preserving Semantic Relations for Zero-Shot Learning , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[3]  Wei Sun,et al.  PD2SE-Net: Computer-assisted plant disease diagnosis and severity estimation network , 2019, Comput. Electron. Agric..

[4]  Zahid Iqbal,et al.  Detection and classification of citrus diseases in agriculture based on optimized weighted segmentation and feature selection , 2018, Comput. Electron. Agric..

[5]  Wei Liu,et al.  Zero-Shot Visual Recognition Using Semantics-Preserving Adversarial Embedding Networks , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[6]  Venkatesh Saligrama,et al.  Zero-Shot Learning via Semantic Similarity Embedding , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[7]  Tiemin Zhang,et al.  Detection of sick broilers by digital image processing and deep learning , 2019, Biosystems Engineering.

[8]  Cordelia Schmid,et al.  Label-Embedding for Attribute-Based Classification , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[9]  David A. Forsyth,et al.  Describing objects by their attributes , 2009, CVPR.

[10]  Georgina Stegmayer,et al.  Automatic recognition of quarantine citrus diseases , 2013, Expert Syst. Appl..

[11]  Hema A. Murthy,et al.  A Generative Model for Zero Shot Learning Using Conditional Variational Autoencoders , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[12]  Zahid Iqbal,et al.  An automated detection and classification of citrus plant diseases using image processing techniques: A review , 2018, Comput. Electron. Agric..

[13]  Shaogang Gong,et al.  Semantic Autoencoder for Zero-Shot Learning , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[14]  Bernt Schiele,et al.  Zero-Shot Learning — The Good, the Bad and the Ugly , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[15]  Christoph H. Lampert,et al.  Zero-Shot Learning—A Comprehensive Evaluation of the Good, the Bad and the Ugly , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[16]  Bin Tong,et al.  Hierarchical Disentanglement of Discriminative Latent Features for Zero-Shot Learning , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[17]  Christoph H. Lampert,et al.  Learning to detect unseen object classes by between-class attribute transfer , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[18]  Jinchang Ren,et al.  SR-GAN: Semantic Rectifying Generative Adversarial Network for Zero-shot Learning , 2019, 2019 IEEE International Conference on Multimedia and Expo (ICME).

[19]  Geoffrey E. Hinton,et al.  Visualizing Data using t-SNE , 2008 .

[20]  Zhengming Ding,et al.  Marginalized Latent Semantic Encoder for Zero-Shot Learning , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[21]  Xi Cheng,et al.  Pest identification via deep residual learning in complex background , 2017, Comput. Electron. Agric..

[22]  Mirtes Costa,et al.  Effects of the essential oil from Citrus aurantium L. in experimental anxiety models in mice. , 2006, Life sciences.

[23]  Yang Song,et al.  Age Progression/Regression by Conditional Adversarial Autoencoder , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[24]  Yufeng Shen,et al.  Detection of stored-grain insects using deep learning , 2018, Comput. Electron. Agric..

[25]  Geyong Min,et al.  An Exploration of Cross-Modal Retrieval for Unseen Concepts , 2019, DASFAA.

[26]  Lingyun Xiang,et al.  A Smart Mobile Diagnosis System for Citrus Diseases Based on Densely Connected Convolutional Networks , 2019, IEEE Access.

[27]  Philip H. S. Torr,et al.  An embarrassingly simple approach to zero-shot learning , 2015, ICML.

[28]  Piyush Rai,et al.  Generalized Zero-Shot Learning via Synthesized Examples , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[29]  Ghulam Muhammad,et al.  Automatic Fruit Classification Using Deep Learning for Industrial Applications , 2019, IEEE Transactions on Industrial Informatics.

[30]  Marely Lee,et al.  Citrus Pests and Diseases Recognition Model Using Weakly Dense Connected Convolution Network , 2019, Sensors.