Human experts vs. machines in taxa recognition
Research output: Contribution to journal › Article › Scientific › peer-review
The step of expert taxa recognition currently slows down the response time of many bioassessments. Shifting to quicker and cheaper state-of-the-art machine learning ap- proaches is still met with expert scepticism towards the ability and logic of machines. In our study, we investigate both the differences in accuracy and in the identification logic of taxo- nomic experts and machines. We propose a systematic approach utilizing deep Convolutional Neural Nets with the transfer learning paradigm and extensively evaluate it over a multilabel and multi-pose taxonomic dataset specifically created for this comparison. We also study the prediction accuracy on different ranks of taxonomic hierarchy in detail. Our results revealed that human experts using actual specimens yield the lowest classification error (CE = 6.1%). However, our proposed, much faster, automated approach using deep Convolutional Neural Nets comes very close to human accuracy (CE = 11.4%). Contrary to previous findings in the literature, we find that for machines following a typical flat classification approach commonly used in machine learning performs better than forcing machines to adopt a hierarchical, local per parent node approach used by human taxonomic experts. Finally, we publicly share our unique dataset to serve as a public benchmark dataset in this field.