{
  "abstract": "Representations learned by vision foundation models pretrained on natural images have been shown to be useful for out-of-domain astronomical images. Performance on scientific downstream tasks increases with model size, which both carries higher inference costs and limits scalability, even when considering parameter-efficient adaptation. An alternative is to learn representations directly from astronomical observations rather than natural images, through self-supervised pretraining. We evaluate LeJEPA's ability to learn robust representations using very small vision models ($\\sim$6M parameters) pretrained on Radio Galaxy Zoo images, comparing with established self-supervised frameworks. We test whether LeJEPA's latent-space regularization leads to better radio galaxy morphology classification. Across three evaluation datasets, LeJEPA achieves performance comparable to a substantially larger foundation model while producing more consistent representations across training and evaluation datasets. These results suggest that the choice of representation learning objective is critical for enabling small domain-specific models to achieve performance competitive with representations transferred from large foundation models in scientific imaging.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2608.30594",
  "author_total": 7,
  "authors": [
    {
      "name": "Erica Lastufka"
    },
    {
      "name": "Mariia Drozdova"
    },
    {
      "name": "Vitaliy Kinakh"
    },
    {
      "name": "Taras Holotyak"
    },
    {
      "name": "Miroslava Dessuages-Zavadsky"
    },
    {
      "name": "Daniel Schaerer"
    },
    {
      "name": "Svyatoslav Voloshynovskiy"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/48gqnap6rm1p0.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2608.30594",
  "fulltext_url": null,
  "id": "48gqnap6rm1p0",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2608.30594",
  "language": null,
  "licence": "CC-BY-NC-ND-4.0",
  "licence_label": "CC BY-NC-ND 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by-nc-nd/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "astro-ph.IM"
    ],
    [
      "openalex",
      "1702|Domain Adaptation and Few-Shot Learning"
    ]
  ],
  "openalex": "W7204882947",
  "pdf_url": "https://arxiv.org/pdf/2608.30594",
  "pmcid": null,
  "pmid": null,
  "published": "2026-08-31",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/48gqnap6rm1p0.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:41Z",
      "native_id": "2608.30594",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2608.30594"
    }
  ],
  "subjects": [
    {
      "field": "astronomy",
      "origin": "arxiv:astro-ph.IM",
      "subfield": "instrumentation-methods"
    }
  ],
  "title": "Learning Radio Astronomical Representations with LeJEPA and Very Small Models",
  "title_text": "Learning Radio Astronomical Representations with LeJEPA and Very Small Models",
  "type": "preprint",
  "updated_at": "2026-10-30T12:17:41Z",
  "url": "https://research.draconitic.com/paper/48gqnap6rm1p0",
  "venue": "arXiv",
  "versions": []
}