Classification of freshwater snails of the genus Radomaniola with multimodal triplet networks
This work addresses a specific problem in biodiversity and taxonomy for researchers, but it is incremental as it applies existing methods to a new dataset.
The paper tackled the classification of freshwater snails in the genus Radomaniola using a multimodal triplet network to address challenges like a small, imbalanced dataset with high visual similarity, achieving performance comparable to a trained domain expert.
In this paper, we present our first proposal of a machine learning system for the classification of freshwater snails of the genus Radomaniola. We elaborate on the specific challenges encountered during system design, and how we tackled them; namely a small, very imbalanced dataset with a high number of classes and high visual similarity between classes. We then show how we employed triplet networks and the multiple input modalities of images, measurements, and genetic information to overcome these challenges and reach a performance comparable to that of a trained domain expert.