Label-efficient underwater species classification with logistic regression on frozen foundation model embeddings

TL;DR

This paper demonstrates that a simple logistic regression classifier on frozen foundation model embeddings can effectively classify underwater species with minimal supervision, matching or surpassing more complex models.

Contribution

It shows that frozen foundation model embeddings enable label-efficient underwater species classification without additional training or domain-specific engineering.

Findings

Logistic regression on frozen embeddings achieves 88.5% macro F1 at full supervision.

With only 21 labeled examples per class, macro F1 exceeds 80%.

The approach requires no fine-tuning or domain-specific data engineering.

Abstract

Automated species classification from underwater imagery is bottlenecked by the cost of expert annotation, and supervised models trained on one dataset rarely transfer to new conditions. We investigate whether a simple classifier operating on frozen foundation model embeddings can close this gap. Using frozen DINOv3 ViT-B/16 embeddings with no fine-tuning, we train a logistic regression classifier and evaluate on the AQUA20 benchmark (20 marine species). At full supervision, logistic regression achieves 88.5% macro F1 compared to ConvNeXt's 88.9%, a gap of 0.4 percentage points, while outperforming the supervised baseline on 8 of 20 species. Under label scarcity, with 21 labeled examples per class (approximately 6% of training labels), macro F1 exceeds 80%. The near-parity with end-to-end supervised learning demonstrates that these general-purpose, frozen representations exhibit strong linear separability at the species level in the underwater domain. Our approach requires no deep learning training, no domain-specific data engineering, and no underwater-adapted models, establishing a practical, immediately deployable baseline for label-efficient marine species recognition. All results are reported on the held-out test set over 100 random seed initialisations. This is a preliminary report; further evaluations and ablations are forthcoming.