# Diffusion Representations for Fine-Grained Image Classification: A Marine Plankton Case Study Source: [Diffusion Representations for Fine-Grained Image Classification: A Marine Plankton Case Study]() Collection index: [llms.txt]() Data updated: 2026-01-22T05:00:31.014Z Authors: A. Nieto Juscafresa, \\'A. Mazcu\\~n\\'an Herreros, J. Sullivan Published: 2026-01-19T21:55:27.000Z ## Abstract 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Image Classification on Unbalanced IFCB Plankton Dataset (test)](): Image Classification; Unbalanced IFCB Plankton Dataset (test); Accuracy: 91.45. - [Image Classification on Balanced IFCB Plankton Dataset (test)](): Image Classification; Balanced IFCB Plankton Dataset (test); Accuracy: 0.924. ## Original sources and implementation [Original paper]() [PDF]()