DFF-ResNet: An Insect Pest Recognition Model Based on Residual Networks
Insect pest control is considered as a significant factor in the yield of commercial crops. Thus, to avoid economic losses, we need a valid method for insect pest recognition. In this paper, we proposed a feature fusion residual block to perform the insect pest recognition task. Based on the origina...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Tsinghua University Press
2020-12-01
|
| Series: | Big Data Mining and Analytics |
| Subjects: | |
| Online Access: | https://www.sciopen.com/article/10.26599/BDMA.2020.9020021 |
| _version_ | 1811250896314564608 |
|---|---|
| author | Wenjie Liu Guoqing Wu Fuji Ren Xin Kang |
| author_facet | Wenjie Liu Guoqing Wu Fuji Ren Xin Kang |
| author_sort | Wenjie Liu |
| collection | DOAJ |
| description | Insect pest control is considered as a significant factor in the yield of commercial crops. Thus, to avoid economic losses, we need a valid method for insect pest recognition. In this paper, we proposed a feature fusion residual block to perform the insect pest recognition task. Based on the original residual block, we fused the feature from a previous layer between two 1×1 convolution layers in a residual signal branch to improve the capacity of the block. Furthermore, we explored the contribution of each residual group to the model performance. We found that adding the residual blocks of earlier residual groups promotes the model performance significantly, which improves the capacity of generalization of the model. By stacking the feature fusion residual block, we constructed the Deep Feature Fusion Residual Network (DFF-ResNet). To prove the validity and adaptivity of our approach, we constructed it with two common residual networks (Pre-ResNet and Wide Residual Network (WRN)) and validated these models on the Canadian Institute For Advanced Research (CIFAR) and Street View House Number (SVHN) benchmark datasets. The experimental results indicate that our models have a lower test error than those of baseline models. Then, we applied our models to recognize insect pests and obtained validity on the IP102 benchmark dataset. The experimental results show that our models outperform the original ResNet and other state-of-the-art methods. |
| first_indexed | 2024-04-12T16:11:36Z |
| format | Article |
| id | doaj.art-30914396c1244792932a68fc9073dd46 |
| institution | Directory Open Access Journal |
| issn | 2096-0654 |
| language | English |
| last_indexed | 2024-04-12T16:11:36Z |
| publishDate | 2020-12-01 |
| publisher | Tsinghua University Press |
| record_format | Article |
| series | Big Data Mining and Analytics |
| spelling | doaj.art-30914396c1244792932a68fc9073dd462022-12-22T03:25:52ZengTsinghua University PressBig Data Mining and Analytics2096-06542020-12-013430031010.26599/BDMA.2020.9020021DFF-ResNet: An Insect Pest Recognition Model Based on Residual NetworksWenjie Liu0Guoqing Wu1Fuji Ren2Xin Kang3<institution>School of Information Science and Technology and School of Transportation and Civil Engineering, Nantong University</institution>, <city>Nantong</city> <postal-code>226019</postal-code>, <country>China</country>, and also with the <institution>Faculty of Engineering, Tokushima University</institution>, <city>Tokushima</city> <postal-code>770-8506</postal-code>, <country>Japan</country><institution>School of Information Science and Technology, Nantong University</institution>, <city>Nantong</city> <postal-code>226019</postal-code>, <country>China</country><institution>Faculty of Engineering, Tokushima University</institution>, <city>Tokushima</city> <postal-code>770-8506</postal-code>, <country>Japan</country><institution>Faculty of Engineering, Tokushima University</institution>, <city>Tokushima</city> <postal-code>770-8506</postal-code>, <country>Japan</country>Insect pest control is considered as a significant factor in the yield of commercial crops. Thus, to avoid economic losses, we need a valid method for insect pest recognition. In this paper, we proposed a feature fusion residual block to perform the insect pest recognition task. Based on the original residual block, we fused the feature from a previous layer between two 1×1 convolution layers in a residual signal branch to improve the capacity of the block. Furthermore, we explored the contribution of each residual group to the model performance. We found that adding the residual blocks of earlier residual groups promotes the model performance significantly, which improves the capacity of generalization of the model. By stacking the feature fusion residual block, we constructed the Deep Feature Fusion Residual Network (DFF-ResNet). To prove the validity and adaptivity of our approach, we constructed it with two common residual networks (Pre-ResNet and Wide Residual Network (WRN)) and validated these models on the Canadian Institute For Advanced Research (CIFAR) and Street View House Number (SVHN) benchmark datasets. The experimental results indicate that our models have a lower test error than those of baseline models. Then, we applied our models to recognize insect pests and obtained validity on the IP102 benchmark dataset. The experimental results show that our models outperform the original ResNet and other state-of-the-art methods.https://www.sciopen.com/article/10.26599/BDMA.2020.9020021insect pest recognitiondeep feature fusionresidual networkimage classification |
| spellingShingle | Wenjie Liu Guoqing Wu Fuji Ren Xin Kang DFF-ResNet: An Insect Pest Recognition Model Based on Residual Networks Big Data Mining and Analytics insect pest recognition deep feature fusion residual network image classification |
| title | DFF-ResNet: An Insect Pest Recognition Model Based on Residual Networks |
| title_full | DFF-ResNet: An Insect Pest Recognition Model Based on Residual Networks |
| title_fullStr | DFF-ResNet: An Insect Pest Recognition Model Based on Residual Networks |
| title_full_unstemmed | DFF-ResNet: An Insect Pest Recognition Model Based on Residual Networks |
| title_short | DFF-ResNet: An Insect Pest Recognition Model Based on Residual Networks |
| title_sort | dff resnet an insect pest recognition model based on residual networks |
| topic | insect pest recognition deep feature fusion residual network image classification |
| url | https://www.sciopen.com/article/10.26599/BDMA.2020.9020021 |
| work_keys_str_mv | AT wenjieliu dffresnetaninsectpestrecognitionmodelbasedonresidualnetworks AT guoqingwu dffresnetaninsectpestrecognitionmodelbasedonresidualnetworks AT fujiren dffresnetaninsectpestrecognitionmodelbasedonresidualnetworks AT xinkang dffresnetaninsectpestrecognitionmodelbasedonresidualnetworks |