On the use of uncertainty in classifying Aedes Albopictus mosquitoes

TL;DR

This paper introduces a method using Monte Carlo Dropout to estimate uncertainty in CNN-based mosquito classification, reducing manual labeling and improving accuracy in identifying Aedes albopictus mosquitoes.

Contribution

It proposes an uncertainty-based ranking and active learning framework to enhance mosquito classification with less manual annotation and better performance.

Findings

Uncertainty estimation improves classification accuracy.

Active learning reduces manual labeling effort.

Explainable visualizations aid understanding of uncertainty.

Abstract

The re-emergence of mosquito-borne diseases (MBDs), which kill hundreds of thousands of people each year, has been attributed to increased human population, migration, and environmental changes. Convolutional neural networks (CNNs) have been used by several studies to recognise mosquitoes in images provided by projects such as Mosquito Alert to assist entomologists in identifying, monitoring, and managing MBD. Nonetheless, utilising CNNs to automatically label input samples could involve incorrect predictions, which may mislead future epidemiological studies. Furthermore, CNNs require large numbers of manually annotated data. In order to address the mentioned issues, this paper proposes using the Monte Carlo Dropout method to estimate the uncertainty scores in order to rank the classified samples to reduce the need for human supervision in recognising Aedes albopictus mosquitoes. The estimated uncertainty was also used in an active learning framework, where just a portion of the data from large training sets was manually labelled. The experimental results show that the proposed classification method with rejection outperforms the competing methods by improving overall performance and reducing entomologist annotation workload. We also provide explainable visualisations of the different regions that contribute to a set of samples' uncertainty assessment.