Feature Reuse Residual Networks for Insect Pest Recognition

Citations Over TimeTop 10% of 2019 papers

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.

Related Papers

• → IR-UWB radar based through-wall human detection with limited data via multi-hop residual CNN(2023)1 cited
• → Depth-Specific Variational Scaling Method to Improve Accuracy of ResNet(2021)2 cited
• → Inception-v4, Inception-ResNet and the Impact of Residual Connections on\n Learning(2016)199 cited
• → Deep Residual Networks and Weight Initialization(2017)13 cited
• Residual Attention Network for Brain Tumour Classification(2019)