LUMOS achieves superior universal semi-supervised OCT retinal layer segmentation via a dual-decoder network with hierarchical prompting and reliable progressive multi-granularity learning for cross-granularity alignment.
Experiments on six datasets demonstrate that LUMOS and its components significantly outperform existing methods in cross-domain and cross-granularity adaptation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
LUMOS: Universal Semi-Supervised OCT Retinal Layer Segmentation with Hierarchical Reliable Mutual Learning
LUMOS achieves superior universal semi-supervised OCT retinal layer segmentation via a dual-decoder network with hierarchical prompting and reliable progressive multi-granularity learning for cross-granularity alignment.