{
  "abstract": "The primate retina is strikingly non-uniform, with receptor density falling off sharply from fovea to periphery. Every eye-movement brings a previously low-acuity peripheral area to high-acuity foveal processing. We hypothesize that this process provides a natural self-supervision signal, enabling representation learning by predicting fine details in the periphery. We implement this in a SimMIM-style vision transformer, replacing its blank masks (ViT-Blank) with a uniform blur mask (ViT-Blur) and further with retinal masks in which a foveal patch is randomly selected, and all other patches are progressively blurred based on eccentricity from the foveal patch (ViT-Retina). ViTs were pre-trained to reconstruct the full-resolution image from the corrupted input and then fine-tuned on clean images for classification. ViT-Blur and ViT-Retina outperform ViT-Blank on the pre-training reconstruction task while controlling for retained information from the input across corruption types. Critically, they also outperform ViT-Blank on downstream classification, showing that they learn representations that generalize better. The ViT-Blur and ViT-Retina are also more robust in impoverishment conditions such as higher mask ratios, fewer pre-training epochs, smaller training sets, and test time image corruptions. Using additive band-limited noise, we discovered that ViT-Blank relies on higher spatial frequencies compared to ViT-Blur and ViT-Retina, and we show this to be the likely cause of poorer generalization: the centroid of a model's spatial frequency tuning is negatively correlated with its classification accuracy ($r = -0.73$). We further show that a closed-form linear-ridge encoder derived from the same reconstruction objective reproduces this tuning ($r = 0.88$). Overall, our experiments show the promise of a biologically-inspired self-supervision objective for learning robust visual representations.",
  "abstract_shown": true,
  "affiliations": [
    "Zuckerman Institute, Columbia University"
  ],
  "article_type": "New results",
  "arxiv": null,
  "author_total": 5,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "A. Maruya"
    },
    {
      "name": "H. Adeli Jelodar"
    },
    {
      "name": "T. Zheng"
    },
    {
      "name": "N. Kriegeskorte"
    },
    {
      "name": "N. Qian"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/9rgjyfy2jmcwa.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.09.26.754698",
  "fulltext_url": "https://www.biorxiv.org/content/10.64898/2026.09.26.754698v1.full",
  "id": "9rgjyfy2jmcwa",
  "issns": [],
  "landing_url": "https://www.biorxiv.org/content/10.64898/2026.09.26.754698v1",
  "language": null,
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "biorxiv",
      "neuroscience"
    ],
    [
      "openalex",
      "1707|Advanced Neural Network Applications"
    ]
  ],
  "openalex": "W7219842053",
  "pdf_url": "https://www.biorxiv.org/content/10.64898/2026.09.26.754698v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-26",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/9rgjyfy2jmcwa.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:25:42Z",
      "native_id": "10.64898/2026.09.26.754698",
      "source": "biorxiv",
      "url": "https://www.biorxiv.org/content/10.64898/2026.09.26.754698v1"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "biorxiv:neuroscience",
      "subfield": "neuroscience"
    }
  ],
  "title": "Foveation as self-supervision signal: Blur masks beat blank masks for learning robust visual representations",
  "title_text": "Foveation as self-supervision signal: Blur masks beat blank masks for learning robust visual representations",
  "type": "preprint",
  "updated_at": "2026-10-30T12:25:42Z",
  "url": "https://research.draconitic.com/paper/9rgjyfy2jmcwa",
  "venue": "bioRxiv",
  "versions": []
}