SEMIR: Semantic Minor-Induced Representation Learning on Graphs for Visual Segmentation

ArXi:2605.12389v1 Announce Type: cross Segmenting small and sparse structures in large-scale images is fundamentally constrained by voxel-level, lattice-bound computation and extreme class imbalance -- dense, full-resolution inference scales poorly and forces most pipelines to rely on fixed regionization or downsampling, coupling computational cost to image resolution and attenuating boundary evidence precisely where minority structures are most informative. We