{
  "abstract": "Biological connectomes encode structured solutions to visual computation that may provide reusable inductive biases for artificial vision. We develop ConnectomeX around FlyVision, a trainable architecture that preserves parallel ON/OFF processing, recurrent computation and population-level graph interaction while scaling model capacity across tasks. FlyVision reached 99.34% accuracy on MNIST with 80,608 parameters and 78.03% on CIFAR-10 with 81,408 parameters. On ImageNet-1K, FlyVision Base and Large reached 60.79% and 66.25% top-1 accuracy with 1.8 and 3.7 million parameters, while a Large local-k7 model with a learned low-frequency branch reached 66.53%, compared with 69.25% for ResNet18 with 11.7 million parameters. On a 22-class skin-disease benchmark, FlyVision Large achieved 63.78% accuracy and 95.28% macro-AUROC with 2.99 million parameters. In four-class chest radiography, ImageNet-pretrained FlyVision Base and Large reached 92.60% and 92.76% accuracy with 1.33 and 2.97 million parameters, compared with 91.56% for ImageNet-pretrained ResNet18 with 11.18 million. BrainAGE extends FlyVision to volumetric T1-weighted MRI by applying a shared ImageNet-pretrained FlyVision Large encoder to 24 sagittal, coronal and axial slices per scan and combining slice-level age estimates by confidence-modulated Gaussian voting. On 433 held-out scans, three-axis fusion achieved a mean absolute error of 5.98 years and R^2 = 0.868. Across the 224x224 classification tasks, the best FlyVision configuration remained within three percentage points of ResNet18 on ImageNet-1K and skin-disease classification and exceeded it on chest radiography with substantially fewer parameters. These results show that a conserved connectome-informed computation can scale from compact recognition to large-scale natural and biomedical vision.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.08418",
  "author_total": 7,
  "authors": [
    {
      "name": "Zongyu Li"
    },
    {
      "name": "Akito Yamauchi"
    },
    {
      "name": "Huaizhi Liu"
    },
    {
      "name": "Vishwanatha Rao"
    },
    {
      "name": "Jia Guo"
    },
    {
      "name": "for the Frontotemporal Lobar Degeneration Neuroimaging Initiative"
    },
    {
      "name": "for the Alzheimer's Disease Neuroimaging Initiative"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/egqa6sjz3v2h6.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.08418",
  "fulltext_url": null,
  "id": "egqa6sjz3v2h6",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.08418",
  "language": null,
  "licence": "LicenseRef-arXiv-nonexclusive-1.0",
  "licence_label": "arXiv licence",
  "licence_source": "article",
  "licence_url": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.CV"
    ],
    [
      "arxiv",
      "cs.NE"
    ],
    [
      "arxiv",
      "q-bio.NC"
    ],
    [
      "openalex",
      "1707|Advanced Neural Network Applications"
    ]
  ],
  "openalex": "W7220940296",
  "pdf_url": "https://arxiv.org/pdf/2610.08418",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-06",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/egqa6sjz3v2h6.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:27:27Z",
      "native_id": "2610.08418",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.08418"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "arxiv:q-bio.NC",
      "subfield": "neuroscience"
    }
  ],
  "title": "From the Drosophila Visual Connectome to General-Purpose Computer Vision",
  "title_text": "From the Drosophila Visual Connectome to General-Purpose Computer Vision",
  "type": "preprint",
  "updated_at": "2026-10-30T12:27:27Z",
  "url": "https://research.draconitic.com/paper/egqa6sjz3v2h6",
  "venue": "arXiv",
  "versions": []
}