Diffusion models have emerged as state-of-the-art generative methods for image synthesis, yet their potential as general-purpose feature encoders remains underexplored. Trained for denoising and generation without labels, they can be interpreted as self-supervised learners that capture both low- and high-level structure. We show that a frozen diffusion backbone enables strong fine-grained recognition by probing intermediate denoising features across layers and timesteps and training a linear classifier for each pair. We evaluate this in a real-world plankton-monitoring setting with practical impact, using controlled and comparable training setups against established supervised and self-supervised baselines. Frozen diffusion features are competitive with supervised baselines and outperform other self-supervised methods in both balanced and naturally long-tailed settings. Out-of-distribution evaluations on temporally and geographically shifted plankton datasets further show that frozen diffusion features maintain strong accuracy and Macro F1 under substantial distribution shift.
@article{arxiv.2601.13416,
title = {Diffusion Representations for Fine-Grained Image Classification: A Marine Plankton Case Study},
author = {A. Nieto Juscafresa and Á. Mazcuñán Herreros and J. Sullivan},
journal= {arXiv preprint arXiv:2601.13416},
year = {2026}
}