NL-MambaXCT: Self-Supervised Nested-Learning Mamba for Nomex Honeycomb X-ray CT Defect Classification
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916050995511296 |
|---|---|
| author | Aldoboni, Ghaleb Nassar, Lobna Karray, Fakhri Alshamsi, Reem |
| author_facet | Aldoboni, Ghaleb Nassar, Lobna Karray, Fakhri Alshamsi, Reem |
| contents | X-ray computed tomography (XCT) is widely used for non-destructive testing of Nomex honeycomb structures in aerospace manufacturing, but industrial inspection still relies heavily on manual interpretation and supervised models trained on limited labeled data. This work introduces NL-MambaXCT, a Mamba-based framework that combines self-supervised masked image modelling with a Nested Learning (NL) formulation for automated, label-efficient defect classification from production XCT slices. The backbone is a four-stage 2D encoder with RegNet convolutional blocks in the early stages and Mamba-based sequence mixing with attention in the deeper stages. It is pretrained by masked image modelling on 19,961 unlabeled industrial XCT slices and fine-tuned on 2,000 relabeled Nomex XCT slices split by production order. NL is instantiated through two-timescale parameter dynamics: selected projections maintain slow exponential-moving-average traces alongside fast weights, while a deep-momentum optimizer introduces an additional slow parameter-update trajectory. On the held-out test set, the MIM-pretrained NL-MambaXCT model achieves 96.91% accuracy and 96.8% macro F1, outperforming CNN, attention, and single-timescale Mamba baselines by 3.11--10.31 percentage points in accuracy. The results suggest that combining masked self-supervision with NL-style fast/ slow learning dynamics is a promising strategy for robust defect classification in Nomex honeycomb XCT inspection. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_27454 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | NL-MambaXCT: Self-Supervised Nested-Learning Mamba for Nomex Honeycomb X-ray CT Defect Classification Aldoboni, Ghaleb Nassar, Lobna Karray, Fakhri Alshamsi, Reem Image and Video Processing Computer Vision and Pattern Recognition X-ray computed tomography (XCT) is widely used for non-destructive testing of Nomex honeycomb structures in aerospace manufacturing, but industrial inspection still relies heavily on manual interpretation and supervised models trained on limited labeled data. This work introduces NL-MambaXCT, a Mamba-based framework that combines self-supervised masked image modelling with a Nested Learning (NL) formulation for automated, label-efficient defect classification from production XCT slices. The backbone is a four-stage 2D encoder with RegNet convolutional blocks in the early stages and Mamba-based sequence mixing with attention in the deeper stages. It is pretrained by masked image modelling on 19,961 unlabeled industrial XCT slices and fine-tuned on 2,000 relabeled Nomex XCT slices split by production order. NL is instantiated through two-timescale parameter dynamics: selected projections maintain slow exponential-moving-average traces alongside fast weights, while a deep-momentum optimizer introduces an additional slow parameter-update trajectory. On the held-out test set, the MIM-pretrained NL-MambaXCT model achieves 96.91% accuracy and 96.8% macro F1, outperforming CNN, attention, and single-timescale Mamba baselines by 3.11--10.31 percentage points in accuracy. The results suggest that combining masked self-supervision with NL-style fast/ slow learning dynamics is a promising strategy for robust defect classification in Nomex honeycomb XCT inspection. |
| title | NL-MambaXCT: Self-Supervised Nested-Learning Mamba for Nomex Honeycomb X-ray CT Defect Classification |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.27454 |