Model Releases
Multimodal Taxonomic Conditioning for Generative Plankton Imagery
arXiv:2609.11673v1 Announce Type: new Abstract: Automated plankton imaging produces severely long-tailed datasets, where the rare taxa of greatest ecological interest have too few images to train or e
arXiv:2609.11673v1 Announce Type: new 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.
Related
- Beyond Static Costs: Learning-Dynamics Aware Loss Functions for Long-Tailed Classification
- RSFusionDet: Underwater RGB-Sonar Multimodal Object Detection
- RareSpot+: A Benchmark, Model, and Active Learning Framework for Small and Rare Wildlife in Aerial Imagery
Source: arXiv cs.CV | 2026-09-11