Multimodal Taxonomic Conditioning for Generative Plankton Imagery
Daniela Ivanova
Ozgu Goksu
Nicolas Pugeault
Sep 2026
Machine Learning
Computer Vision
Abstract
Automated plankton imaging produces severely long-tailed datasets, where the rare taxa of greatest ecological interest have too few images to train or evaluate classifiers reliably. We generate synthetic plankton imagery conditioned on taxonomy: a CLIP encoder is adapted on a large plankton corpus with a ranked contrastive objective extended to deep, ragged taxonomies, then frozen to condition a parameter-efficient diffusion transformer. We evaluate synthetic sample quality on distributional fidelity and downstream classifier utility.
