Feature Reuse Residual Networks for Insect Pest Recognition

Abstract

Insect pests are one of the main threats to the commercially important crops. An effective insect pest recognition method can avoid economic losses. In this paper, we proposed a new and simple structure based on the original residual block and named as feature reuse residual block which combines feature from the input signal of a residual block with the residual signal. In each feature reuse residual block, it enhances the capacity of representation by learning half and reuse half feature. By stacking the feature reuse residual block, we obtained the feature reuse residual network (FR-ResNet) and evaluated the performance on IP102 benchmark dataset. The experimental results showed that FR-ResNet can achieve significant performance improvement in terms of insect pest classification. Moreover, to demonstrate the adaptive of our approach, we applied it to various kinds of residual networks, including ResNet, Pre-ResNet, and WRN, and we tested the performance on a series of benchmark datasets: CIFAR-10, CIFAR-100, and SVHN. The experimental results showed that the performance can be improved obviously than original networks. Based on these experiments on CIFAR-10, CIFAR-100, SVHN, and IP102 benchmark datasets, it demonstrates the effectiveness of our approach. INDEX TERMS Insect pest recognition, feature reuse, residual network.

DFF-ResNet: An insect pest recognition model based on residual networks

“…Dimililer and Zarrouk [28] proposed a two stage method for detecting and classifying eight insects based on neural networks. In addition, Ren et al [4] proposed a feature reuse residual network to recognize insect pests.…”

“…The RoR [32] further develops the optimization ability of the network by adding shortcut connections based on the original residual network. Therefore, an increasing number of residual network variants form a residual-network family together [4,6,9,21,[30][31][32] .…”

“…Therefore, we need a valid detection method to accelerate the process of insect pest recognition. Deep learning technology, as an emerging hot technology, has increasingly attracted attention, and many advanced methods depending on this technology have been applied in every field including insect pest recognition [2][3][4] .…”

Putting deep learning in perspective for pest management scientists

“…DL has been slow in coming to pest management per se , but it has begun to make itself felt in agriculture in general . Exemplary applications include insect pest identification, identifying weeds in crops, and differentiating between plant diseases . Such tasks are directly analogous to tasks DL tools were developed to solve, i.e.…”

“…Much of the DL literature is steeped in jargon, but there are many excellent general reviews available that range from the very general to ones that focus on pharmaceutical or agricultural research and development. The examples of pest management applications discussed herein were chosen because they include good summaries of previous work in their respective areas.…”