Visual Microfossil Identification via Deep Metric Learning

TL;DR

This paper demonstrates that deep metric learning significantly improves the classification and visualization of planktic foraminifer shells in microscopic images, outperforming existing CNN methods and enabling open-set species clustering.

Contribution

It introduces the first application of deep metric learning to microfossil classification, providing visualization of phenotypic space and effective clustering of unseen species.

Findings

Achieved 92% accuracy on expert-labeled data.

Outperformed existing CNN benchmarks.

Enabled clustering of unseen species with 66.5% accuracy.

Abstract

We apply deep metric learning for the first time to the problem of classifying planktic foraminifer shells on microscopic images. This species recognition task is an important information source and scientific pillar for reconstructing past climates. All foraminifer CNN recognition pipelines in the literature produce black-box classifiers that lack visualization options for human experts and cannot be applied to open-set problems. Here, we benchmark metric learning against these pipelines, produce the first scientific visualization of the phenotypic planktic foraminifer morphology space, and demonstrate that metric learning can be used to cluster species unseen during training. We show that metric learning outperforms all published CNN-based state-of-the-art benchmarks in this domain. We evaluate our approach on the 34,640 expert-annotated images of the Endless Forams public library of 35 modern planktic foraminifera species. Our results on this data show leading 92% accuracy (at 0.84 F1-score) in reproducing expert labels on withheld test data, and 66.5% accuracy (at 0.70 F1-score) when clustering species never encountered in training. We conclude that metric learning is highly effective for this domain and serves as an important tool towards expert-in-the-loop automation of microfossil identification. Keycode, network weights, and data splits are published with this paper for full reproducibility.