NL-MambaXCT combines masked image modeling pretraining with nested learning in a hybrid RegNet-Mamba encoder to reach 96.91% accuracy on Nomex honeycomb XCT defect classification using limited labels.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.IV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
NL-MambaXCT: Self-Supervised Nested-Learning Mamba for Nomex Honeycomb X-ray CT Defect Classification
NL-MambaXCT combines masked image modeling pretraining with nested learning in a hybrid RegNet-Mamba encoder to reach 96.91% accuracy on Nomex honeycomb XCT defect classification using limited labels.