Grape disease image classification based on lightweight convolution neural networks and channelwise attention

Tang, Zhe; Yang, Jialing; Li, Zhe; Qi, Fang

doi:10.1016/j.compag.2020.105735

Cited by 127 publications

(60 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…LeafNet [25] presented the usage of CNN on LeafSnap, Flavia, and Foliage [26] datasets and acquired accuracy of 79.66%, 98.69% and 98.75% with iterations of 200,000, 30,000 and 100,000, respectively. For automatic detection and recognition of plant diseases through mobile devices, a comparison of different CNN architectures was performed by [27]. The result of this comparison was that AlexNet achieves higher accuracy of 99.1% with 12,000 iterations; however, regarding complexity, MobileNet gave the best performance under the same epochs.…”

Section: Literature Reviewmentioning

confidence: 99%

Performance of MobileNetV3 Transfer Learning on Handheld Device-based Real-Time Tree Species Identification

Hussain

Barua

Osman

et al. 2021

2021 26th International Conference on Automation and Computing (ICAC)

View full text Add to dashboard Cite

Section: Literature Reviewmentioning

confidence: 99%

Performance of MobileNetV3 Transfer Learning on Handheld Device-based Real-Time Tree Species Identification

Hussain

Barua

Osman

et al. 2021

2021 26th International Conference on Automation and Computing (ICAC)

View full text Add to dashboard Cite

“…In this paper, unlike the traditional research that only uses lightweight models [20][21][22][23]47], we combine pruning, distillation, and quantization methods to minimize the size of the model while ensuring accuracy. Compared with existing lightweight models, our proposed model compression method on VGGNet and AlexNet yields more competitive results (see Section 4.3 for details).…”

Section: Architectures For Plant Disease Detectionmentioning

confidence: 99%

“…Researchers in [19] deployed a lightweight neural network after knowledge distillation on an agricultural robot platform to distinguish between weeds and crops. In [20][21][22][23], authors used lightweight CNNs to identify diseased crop leaves for easier deployment on embedded devices. However, in a related study of model compression [24], a lightweight network was only one part of the solution.…”

Section: Introductionmentioning

confidence: 99%

Deep Neural Network Compression for Plant Disease Recognition

Wang

Ding

et al. 2021

Symmetry

View full text Add to dashboard Cite

Deep neural networks (DNNs) have become the de facto standard for image recognition tasks, and their applications with respect to plant diseases have also obtained remarkable results. However, the large number of parameters and high computational complexities of these network models make them difficult to deploy on farms in remote areas. In this paper, focusing on the problems of resource constraints and plant diseases, we propose a DNN-based compression method. In order to reduce computational burden, this method uses lightweight fully connected layers to accelerate reasoning, pruning to remove redundant parameters and reduce multiply–accumulate operations, knowledge distillation instead of retraining to restore the lost accuracy, and then quantization to compress the size of the model further. After compressing the mainstream VGGNet and AlexNet models, the compressed versions are applied to the Plant Village dataset of plant disease images, and a performance comparison of the models before and after compression is obtained to verify the proposed method. The results show that the model can be compressed to 0.04 Mb with an accuracy of 97.09%. This experiment also proves the effectiveness of knowledge distillation during the pruning process, and compressed models are more efficient than prevalent lightweight models.

show abstract

“…The other way is to solve the classification problem with few data, also called few-shot learning, which is more suitable for practical applications. For example, some other works focused on model compression by pruning [ 23 ], shallow model [ 24 ], and lightweight network [ 25 ].…”

Section: Introductionmentioning

confidence: 99%

Semi-supervised few-shot learning approach for plant diseases recognition

Chao

2021

Plant Methods

105

View full text Add to dashboard Cite

Background Learning from a few samples to automatically recognize the plant leaf diseases is an attractive and promising study to protect the agricultural yield and quality. The existing few-shot classification studies in agriculture are mainly based on supervised learning schemes, ignoring unlabeled data's helpful information. Methods In this paper, we proposed a semi-supervised few-shot learning approach to solve the plant leaf diseases recognition. Specifically, the public PlantVillage dataset is used and split into the source domain and target domain. Extensive comparison experiments considering the domain split and few-shot parameters (N-way, k-shot) were carried out to validate the correctness and generalization of proposed semi-supervised few-shot methods. In terms of selecting pseudo-labeled samples in the semi-supervised process, we adopted the confidence interval to determine the number of unlabeled samples for pseudo-labelling adaptively. Results The average improvement by the single semi-supervised method is 2.8%, and that by the iterative semi-supervised method is 4.6%. Conclusions The proposed methods can outperform other related works with fewer labeled training data.

show abstract

Grape disease image classification based on lightweight convolution neural networks and channelwise attention

Cited by 127 publications

References 21 publications

Performance of MobileNetV3 Transfer Learning on Handheld Device-based Real-Time Tree Species Identification

Performance of MobileNetV3 Transfer Learning on Handheld Device-based Real-Time Tree Species Identification

Deep Neural Network Compression for Plant Disease Recognition

Semi-supervised few-shot learning approach for plant diseases recognition

Contact Info

Product

Resources

About