Reproduce “X-ray illicit object detection using hybrid CNN-transformer neural network architectures” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Jorgen Cani, Christos Diou, Spyridon Evangelatos, Panagiotis Radoglou-Grammatikis, Vasileios Argyriou, Panagiotis Sarigiannidis, Iraklis Varlamis, Georgios Th. Papadopoulos
A comparative study of hybrid CNN-transformer architectures for X-ray security screening demonstrates improved detection robustness across multiple scanner types, with YOLOv8-based detectors using Next-ViT-S backbones achieving superior performance on the EDS dataset while maintaining computational efficiency compared to CNN-only approaches.
Key insights
- Hybrid models showed better robustness to scanner variations than CNN-only approaches
- YOLOv8-based detection heads outperformed RT-DETR for X-ray security applications
- Transformer components improved detection of fine-grained patterns and hidden objects
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.