From the Drosophila Visual Connectome to General-Purpose Computer Vision

Key points

• Biological connectomes encode structured solutions to visual computation that may provide reusable inductive biases for artificial vision.1
• 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.1
• 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.1
• These results show that a conserved connectome-informed computation can scale from compact recognition to large-scale natural and biomedical vision.1

Sources (1)

• [1]From the Drosophila Visual Connectome to General-Purpose Computer Vision
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 6, 02:22 PM

  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.

  Biological connectomes encode structured solutions to visual computation that may provide reusable inductive biases for artificial vision.

Extractive summary: sentences quoted from the sources.