# Planktonzilla: Multimodal dataset and models for understanding plankton ecosystems

arXiv: https://arxiv.org/abs/2606.00080 · HTML: https://mlsanity.com/paper/2606.00080/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 26 references that are in the map.
- First posted on arXiv 22 May 2026.

## Builds on (most cited first, 8 of 8)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learning](https://mlsanity.com/paper/1911.04623/) (2019)
- [BioCLIP: A Vision Foundation Model for the Tree of Life](https://mlsanity.com/paper/2311.18803/) (2023)
- [BioCLIP 2: Emergent Properties from Scaling Hierarchical Contrastive Learning](https://mlsanity.com/paper/2505.23883/) (2025)
- [Deep Learning Classification of Lake Zooplankton](https://mlsanity.com/paper/2108.05258/) (2021)
- [DAPlankton: Benchmark Dataset for Multi-instrument Plankton Recognition via Fine-grained Domain Adaptation](https://mlsanity.com/paper/2402.05615/) (2024)
- [Self-Supervised Pretraining for Fine-Grained Plankton Recognition](https://mlsanity.com/paper/2503.11341/) (2025)

## Built on by (most cited first, 1 of 1)

- [Multimodal Taxonomic Conditioning for Generative Plankton Imagery](https://mlsanity.com/paper/2609.11673/) (2026)

## Abstract (arXiv)

Marine plankton underpin aquatic food webs and play a key role in global CO2 sequestration, making reliable species identification critical for understanding ocean health and climate feedbacks. Existing classification models perform well on individual collections but fail to generalize across instruments and environments due to isolated training datasets and inconsistent labels. To address this, we introduce Planktonzilla-17M, a unified dataset consolidating publicly available plankton image collections spanning thirteen imaging systems. It comprises 17.4 million images with standardized taxonomy and geo-environmental metadata, including 3.74 million plankton images spanning over 602 taxonomic classes, of which 201 are identified at the species level, making it the largest and most comprehensive plankton image dataset to date. Using this large-scale dataset, we perform a controlled comparison between supervised and CLIP-style image--text training on a shared ViT backbone. We find that a supervised classifier matches or exceeds CLIP-style training when trained using taxonomic lineage as text. We further observe that BioCLIP and BioCLIP2 perform poorly on plankton in zero-shot and few-shot settings. Leveraging Planktonzilla-17M improves plankton classification performance, highlighting the limitations of current biological foundation models in marine imaging domains.