Saved in:
Bibliographic Details
Main Authors: Vetter, Dennis, Ahsan, Muhammad, Delicado, Diana, Neubauer, Thomas A., Wilke, Thomas, Roig, Gemma
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2407.20013
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909274139000832
author Vetter, Dennis
Ahsan, Muhammad
Delicado, Diana
Neubauer, Thomas A.
Wilke, Thomas
Roig, Gemma
author_facet Vetter, Dennis
Ahsan, Muhammad
Delicado, Diana
Neubauer, Thomas A.
Wilke, Thomas
Roig, Gemma
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2407_20013
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Classification of freshwater snails of the genus Radomaniola with multimodal triplet networks
Vetter, Dennis
Ahsan, Muhammad
Delicado, Diana
Neubauer, Thomas A.
Wilke, Thomas
Roig, Gemma
Computer Vision and Pattern Recognition
Machine Learning
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.
title Classification of freshwater snails of the genus Radomaniola with multimodal triplet networks
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2407.20013