High performing ensemble of convolutional neural networks for insect pest image detection

TL;DR

This paper develops an ensemble of diverse CNNs with novel Adam optimizers for insect pest image detection, achieving state-of-the-art accuracy and demonstrating robustness across multiple datasets.

Contribution

Introduces new Adam variants based on DGrad and combines multiple CNN topologies with data augmentation for improved pest detection accuracy.

Findings

Achieved 95.52% accuracy on Deng pest dataset.

Achieved 73.46% accuracy on IP102 pest dataset.

Validated robustness on medical image datasets.

Abstract

Pest infestation is a major cause of crop damage and lost revenues worldwide. Automatic identification of invasive insects would greatly speedup the identification of pests and expedite their removal. In this paper, we generate ensembles of CNNs based on different topologies (ResNet50, GoogleNet, ShuffleNet, MobileNetv2, and DenseNet201) altered by random selection from a simple set of data augmentation methods or optimized with different Adam variants for pest identification. Two new Adam algorithms for deep network optimization based on DGrad are proposed that introduce a scaling factor in the learning rate. Sets of the five CNNs that vary in either data augmentation or the type of Adam optimization were trained on both the Deng (SMALL) and the large IP102 pest data sets. Ensembles were compared and evaluated using three performance indicators. The best performing ensemble, which combined the CNNs using the different augmentation methods and the two new Adam variants proposed here, achieved state of the art on both insect data sets: 95.52% on Deng and 73.46% on IP102, a score on Deng that competed with human expert classifications. Additional tests were performed on data sets for medical imagery classification that further validated the robustness and power of the proposed Adam optimization variants. All MATLAB source code is available at https://github.com/LorisNanni/.