Pest Identification Based on Fusion of Self-Attention With ResNet

Abstract

Pest identification is a challenging task in the agricultural sector, as accurate and timely detection of pests is essential for effective pest control and crop protection. Conventional approaches to pest detection, such as entomological knowledge and manual examination, take a lot of time and are prone to human mistakes. The advent of Deep Learning(DL) techniques has revolutionized the field of computer vision, enabling automated and efficient pest recognition systems.In this research, we compared the effectiveness of many deep learning models and suggested an enhanced approach for more effective feature extraction. In the proposed approach, we have incorporated two parallel attention mechanisms in ResNet architectures and it has a significant improvement in performance. Experimental result shows that the performance accuracy obtained in ResNet50-SA, ResNet101-SA, and ResNet152-SA is 99.80%, 88.48% and 96.68%, respectively. The performance of ResNet50-SA outperforms the other state of art deep learning by a large margin. The result shows that ResNet with self-attention (SA) has a better ability to extract features and focus on the important features which increases the performance.

An Advancing GCT-Inception-ResNet-V3 Model for Arboreal Pest Identification

“…In this research, we adopted the ResNet-18 model as the baseline for pest identification studies due to its prominence in previous research [15,16]. The hyperparameters for the ResNet-18 were meticulously adjusted to suit the IP102 dataset's requirements, implementing a grid search for the optimal set.…”

“…Automated systems using machine learning offer a promising solution, yet they require vast amounts of data and computational resources, often lacking in field conditions [14]. The ResNet architecture, with its deep residual learning framework [15,16], offers a potential improvement in learning complex features for accurate pest identification, yet like other advanced CNN (Convolutional Neural Network) architectures (e.g., VGG16 [17,18], DenseNet [19], and Inception-V3 [20][21][22]), it faces challenges in deployment on resource-constrained mobile devices, thus restricting their accessibility. Additionally, memory-efficient CNN architectures [23,24], although apt for mobile environments, typically sacrifice classification precision.…”

“…These models were compared against the traditional ResNet-18 model, which was selected as the control group. The selection of ResNet-18 as the baseline model is due to its widespread adoption in previous research on pest and disease identification [15][16][17], alongside SE-RegNet, SE-SE-RegNet, SE-RegNetY, and GCT-Inception-ResNet-V3. The GCT-Inception-ResNet-V3 model significantly outperforms the baseline model group.…”

Advancing Spatiotemporal Pollutant Dispersion Forecasting with an Integrated Deep Learning Framework for Crucial Information Capture

“…In this study, we proposed a deep learning architecture incorporating a Residual Neural Network (ResNet) and a Temporal Convolutional Network (TCN), called SAResNet-TCN, which aims to adequately capture the spatial and temporal features of pollutant dispersion. ResNet solves the degradation problem in training deep CNNs by introducing residual learning, which allows the network to learn a deeper representation of the features [16,17]. With residual connectivity, the model effectively avoids information loss when training deep models and mitigates the problem of gradient vanishing [18,19].…”