SEMIR replaces dense voxel computation with a learned topology-preserving graph minor that supports exact decoding and GNN-based inference for small-structure segmentation in large medical images.
Multi-class geospatial object detection and geographic image classification based on collection of part detectors
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
-
SEMIR: Semantic Minor-Induced Representation Learning on Graphs for Visual Segmentation
SEMIR replaces dense voxel computation with a learned topology-preserving graph minor that supports exact decoding and GNN-based inference for small-structure segmentation in large medical images.