AI RESEARCH
LUMOS: Universal Semi-Supervised OCT Retinal Layer Segmentation with Hierarchical Reliable Mutual Learning
arXiv CS.CV
•
ArXi:2604.05388v1 Announce Type: new Optical Coherence Tomography (OCT) layer segmentation faces challenges due to annotation scarcity and heterogeneous label granularities across datasets. While semi-supervised learning helps alleviate label scarcity, existing methods typically assume a fixed granularity, failing to fully exploit cross-granularity supervision.