Classification of Canker on Small Datasets Using Improved Deep Convolutional Generative Adversarial Networks

• Published in: IEEE access Vol. 7; pp. 49680 - 49690
• Main Authors: Zhang, Min, Liu, Shuheng, Yang, Fangyun, Liu, Ji
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2019; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Back propagation; Biological system modeling; Classification; Computational modeling; Datasets; Deep learning; Error signals; feature magnification; Gallium nitride; Generative adversarial networks; Machine learning; Optimization; optimization objective breakdown; Siamese learning; Task analysis; Training; Visualization
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2019.2900327

This paper proposes a deep learning model for the classification of citrus canker that overcomes the shortcomings of traditional approaches, and the scarce number of available images for training, which have been subject to the overfitting limitation. To address the issues, we propose two approaches, namely, the feature magnification and objective breakdown optimization, to augment datasets, and emphasizes meaningful features and prevent the model from overfitting noise signals. The first approach mimics the distribution of positive samples with a generative model based on deep convolutional generative adversarial networks. The second approach updates different parts of the model with optimization objectives, whereby back-propagated error signals are no longer the only signal for updating parameters. To validate the proposed approaches, we present theoretical proofs to justify the correctness of our methods and conduct extensive case studies and experiments to show that the proposed approaches clearly outperform traditional approaches on the classification of accuracy and efficiency of small training sets. In this paper, a methodology is proposed to generate a general model. The model can be applied to other bio-medical applications, where the scarcity of visual samples makes it difficult for a normal deep learning model to work without overfitting.