Abstract

Deep learning for computer vision has shown promising results in the field of entomology. Deep learning performance is maximized primarily by bulk labeled data which, outside of rare circumstances, are limited in ecological studies. Currently, to utilize deep learning systems, ecologists undergo extensive data collection efforts, or limit their problem to niche tasks. These solutions do not scale to region agnostic models. There are solutions using data augmentation, simulators, generative models, and self-supervised learning that supplement limited data labels. Here, we highlight the success of deep learning for computer vision within entomology, discuss data collection efforts, provide methodologies for annotation efficient learning, and conclude with practical guidelines for how ecologists can empower accessible automated ecological monitoring on a global scale.