DFF-ResNet: An Insect Pest Recognition Model Based on Residual Networks
DFF-ResNet: An Insect Pest Recognition Model Based on Residual Networks
复制标题
DOI：
10.26599/bdma.2020.9020021
复制
发表时间：
2020-12-01
影响因子：
13.6
通讯作者：
Kang, Xin
中科院分区：
文献类型：
--
作者：
Liu, Wenjie;Wu, Guoqing;Kang, Xin
虫害防治被认为是经济作物产量的一个重要因素。因此，为了避免经济损失，我们需要一种有效的害虫识别方法。在本文中，我们提出了一个特征融合的残留块来执行害虫识别任务。在原始残差块的基础上，将前一层的特征融合到残差信号分支中的两个1 × 1卷积层之间，以提高残差块的容量。此外，我们探讨了每个残差组对模型性能的贡献。我们发现，增加早期残差组的残差块显著提高了模型的性能，从而提高了模型的泛化能力。通过堆叠特征融合残差块，我们构建了深度特征融合残差网络（DFF-ResNet）。为了证明我们的方法的有效性和适应性，我们用两个常见的残差网络（Pre-ResNet和Wide Residual Network（WRN））构建了它，并在加拿大高级研究所（CIFAR）和街景门牌号（SVHN）基准数据集上验证了这些模型。实验结果表明，我们的模型具有较低的测试误差比基线模型。然后，我们将我们的模型应用于识别害虫，并在IP 102基准数据集上取得了有效性。实验结果表明，我们的模型优于原始ResNet和其他最先进的方法。
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 x 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.