[
    {
        "id": "osp-17905",
        "type": "article-journal",
        "title": "From the Drosophila Visual Connectome to General-Purpose Computer Vision",
        "author": [
            {
                "family": "Li",
                "given": "Zongyu"
            },
            {
                "family": "Yamauchi",
                "given": "Akito"
            },
            {
                "family": "Liu",
                "given": "Huaizhi"
            },
            {
                "family": "Rao",
                "given": "Vishwanatha"
            },
            {
                "family": "Guo",
                "given": "Jia"
            },
            {
                "family": "Initiative",
                "given": "for the Frontotemporal Lobar Degeneration Neuroimaging"
            },
            {
                "family": "Initiative",
                "given": "for the Alzheimer's Disease Neuroimaging"
            }
        ],
        "URL": "https://omanscience.com/en/articles/from-the-drosophila-visual-connectome-to-general-purpose-computer-vision",
        "language": "en",
        "issued": {
            "date-parts": [
                [
                    2026
                ]
            ]
        },
        "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."
    }
]