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

[2604.00313] Label-efficient underwater image classification with logistic regression on frozen foundation model embeddings Skip to main content Search Submit Donate Log in Computer Science > Computer Vision and Pattern Recognition arXiv:2604.00313 (cs) [Submitted on 31 Mar 2026 ( v1 ), last revised 24 Aug 2026 (this version, v3)] Title: Label-efficient underwater image classification with logistic regression on frozen foundation model embeddings Authors: Thomas Manuel Rost , Martina Figlia , F. Morgado-Dias , Marko Radeta View PDF HTML (experimental) Abstract: Underwater image classification is constrained by the cost of annotation and by the computational and methodological requirements of task-specific model development. We investigate whether frozen general-purpose foundation-model embeddings can reduce these requirements by extracting DINOv3 ViT-B/16 embeddings and training only a logistic regression classifier on the AQUA20 benchmark. We evaluate the approach across a range of annotation budgets, a repeated 80% training-subsample evaluation, and a full-training refit. With only 13 labelled images per category, corresponding to approximately 4% of the benchmark's official training partition, mean macro F1 reaches 81.8%; with 144 images per category it reaches 88.5%, compared to the published fully supervised ConvNeXt point estimate of 88.9% obtained with the complete training set (benchmark results reported without run-to-run variability). Using all official training labels, macro F1 reaches 91.5% (bootstrap 95% CI: 89.0-93.7%). Sensitivity analyses show that the main findings remain stable across ordinary downstream implementation choices, and persist after removing duplicate and near-duplicate test images identified in an audit of the official split. Preliminary evaluation on a second dataset suggests that overall performance level and the shape of the label efficiency curve are not unique to the AQUA20 dataset. Because the DINOv3 backbone remains frozen and only the downstream classifier is fitted, the approach avoids task-specific neural-network training and can be executed on commodity hardware. These findings establish linear classification on frozen foundation-model embeddings as a practical baseline for label-efficient underwater image classification. Comments: v3. Updated to most recent version Subjects: Computer Vision and Pattern Recognition (cs.CV) Cite as: arXiv:2604.00313 [cs.CV] (or arXiv:2604.00313v3 [cs.CV] for this version) https://doi.org/10.48550/arXiv.2604.00313 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Thomas Rost [ view email ] [v1] Tue, 31 Mar 2026 23:27:09 UTC (22,979 KB) [v2] Wed, 15 Apr 2026 20:28:57 UTC (21,058 KB) [v3] Mon, 24 Aug 2026 19:38:30 UTC (18,665 KB) Full-text links: Access Paper: View PDF HTML (experimental) TeX Source view license Ancillary-file links: Ancillary files ( details ) : arxiv_supplementary.pdf Additional Features Audio Summary Current browse context: cs.CV < prev | next > new | recent | 2026-04 Change to browse by: cs References & Citations SciX Google Scholar Semantic Scholar export BibTeX citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab)

Related documents

• Label-efficient underwater image classification with logistic regression on frozen foundation model embeddings#670542
• HydroMap: Probabilistic Water Surface Elevation Mapping for Semantic Scene Representation in Inland Waterways#1149478
• M3D-Net: Hierarchical Coordination of Spatial Context, Feature Reuse, and Differential Attention for Mammography Classification#1064067
• DiverReef: The global repository of divers' and snorkelers' behavior during tourism activities and their interactions with reef environments over 20 years#1019326
• MVDG: Efficient Multi-view 3D Disambiguation on Unconstrained Real-World Images#1156033