Metraipolis › archive › dc_7154071df398
CRaFT-XDet: Causal and Robust Fusion Transformer for Dual-Energy X-ray Prohibited Item Detection — arXiv:2611.00072
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.00072
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T11:04:33.961Z
- SHA-256 of the archived text
fb04c5e9a9d09042cba7008f802e7d5f0f7a78f71bd69f7acbc5d3c1cf2daddd- Stable URL of this page
https://metraipolis.com/documento/dc_7154071df398
How to cite
CRaFT-XDet: Causal and Robust Fusion Transformer for Dual-Energy X-ray Prohibited Item Detection — arXiv:2611.00072 — arXiv (en), https://arxiv.org/abs/2611.00072 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7154071df398 (Metraipolis archive dc_7154071df398, sha256 fb04c5e9a9d09042cba7008f802e7d5f0f7a78f71bd69f7acbc5d3c1cf2daddd)
BibTeX
@misc{dc7154071df398,
title = {CRaFT-XDet: Causal and Robust Fusion Transformer for Dual-Energy X-ray Prohibited Item Detection — arXiv:2611.00072},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.00072},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7154071df398; sha256 fb04c5e9a9d09042cba7008f802e7d5f0f7a78f71bd69f7acbc5d3c1cf2daddd},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00072. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Automated prohibited item detection in X-ray security imagery is fundamentally constrained by severe object overlap, scanner-dependent domain shifts, and spurious correlations induced by cluttered baggage composition. Existing detectors largely rely on appearance-driven supervision, limiting their robustness and cross-scanner generalisation. We introduce CRaFT-XDet, a causality-grounded and physics- motivated detection framework that reformulates X-ray threat detection as invariant representation learning under attenuation-driven modality variation. Our approach is grounded in a Scanner-Invariant Causal Detection formalisation (Theorem 1), which establishes that minimising the proposed Causal Invariance Regularisation (CIR) objective across partitioned scanner environments approximates the interventional distribution P (Y | do(Xobj)) under standard identifiability assumptions, providing a principled causal formulation for dual-energy X-ray detection. CRaFT-XDet integrates: (i) causal feature disentanglement to suppress context-induced shortcuts; (ii) physics-motivated regularisation to enforce material-consistent embeddings; and (iii) transformer-based cross-energy interaction modelling for structured reasoning in cluttered scenes. With 29.2 M parameters, 89.5 GFLOPs, and 345 FPS (1.7 ms inference), CRaFT-XDet is real-time deployable. Trained on SIXray with five-fold cross-validation, the framework achieves 0.9389 [email protected] and 0.8021 [email protected]:0.95. Without domain adaptation, CRaFT-XDet maintains strong cross- dataset performance on OPIXray and HiXray, indicating robust generalization across heterogeneous scanner distributions. In category-agnostic binary threat detection, the model attains 93.92% recall and 0.9031 mean IoU, highlighting reliability in safety-critical screening where missed detections are costly. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2611.00072 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-03T10:59:45.914Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).