A Lightweight Attention-Based Convolutional Neural Networks for Tomato Leaf Disease Classification

Abstract

Plant diseases pose a significant challenge for food production and safety. Therefore, it is indispensable to correctly identify plant diseases for timely intervention to protect crops from massive losses. The application of computer vision technology in phytopathology has increased exponentially due to automatic and accurate disease detection capability. However, a deep convolutional neural network (CNN) requires high computational resources, limiting its portability. In this study, a lightweight convolutional neural network was designed by incorporating different attention modules to improve the performance of the models. The models were trained, validated, and tested using tomato leaf disease datasets split into an 8:1:1 ratio. The efficacy of the various attention modules in plant disease classification was compared in terms of the performance and computational complexity of the models. The performance of the models was evaluated using the standard classification accuracy metrics (precision, recall, and F1 score). The results showed that CNN with attention mechanism improved the interclass precision and recall, thus increasing the overall accuracy (>1.1%). Moreover, the lightweight model significantly reduced network parameters (~16 times) and complexity (~23 times) compared to the standard ResNet50 model. However, amongst the proposed lightweight models, the model with attention mechanism nominally increased the network complexity and parameters compared to the model without attention modules, thereby producing better detection accuracy. Although all the attention modules enhanced the performance of CNN, the convolutional block attention module (CBAM) was the best (average accuracy 99.69%), followed by the self-attention (SA) mechanism (average accuracy 99.34%).

BWENet: Detection and Grading of Bacterial Wilt Using Deep Convolutional Neural Network

“…When we train our model, learning rate (LR) is too small, over fitting occurred. Large learning rates help to regularize the training (15) but if the learning rate is too large, the training will diverge. Hence empirical short Runs to find learning rates that converge or diverge is possible first, in our case the learning rate are too small to make any progress at all.…”

“…the number of units has to be multiplied by 1/ (dropout rate). Recommended values for the dropout rate are less than 0.5 for the input layer and between 0.5 and 0.8 for hidden layers (15) . In our case we have introduced new model and applied dropout on input layer train with by added different dropout rate 0.1, 0.2, 0.3, 0.4, 0.5 and achieved better result and control overfitting and underfitting at P=0.1.…”

“…They reviewed and conducted using the N-BaIoTdataset, achieving detection accuracies of 90.88 percent and 88.61 percent for Dominion and Ennio brands, respectively, and overall accuracy of 89.64 percent for nine IoT devices infected by ten attacks. (15) Proposed the Lightweight based CNN method to identify tomato leaf disease, they used tomato leaf disease datasets and divided them into 8;1:1 ratios, resulting in a total of 19,510 images from 10 distinct disease classes and one healthy class. They compared the proposed model to other state-of-the-art CNN models in terms of performance and computational complexity, and at the end, the model achieved an average accuracy of 99.34%.…”

A Five Convolutional Layer Deep Convolutional Neural Network for Plant Leaf Disease Detection

“…They achieved a classification accuracy of 98.20% on disease detection. Most recently, the authors of [29] proposed attention-based convolutional neural networks for tomato leaf disease classification. The model achieved a classification accuracy of 99.69% on the test dataset.…”

A Hybrid Model for Leaf Diseases Classification Based on the Modified Deep Transfer Learning and Ensemble Approach for Agricultural AIoT-Based Monitoring

“…In a study by Bhujel et al [ 33 ], the performance of the models was improved by using a lightweight convolution neural network with several attention modules. They were able to train their models with data about tomato leaf diseases.…”