Taming Generative Synthetic Data for X-Ray Prohibited Item Detection

Summary

The paper proposes Xsyn, a one-stage X-ray security image synthesis pipeline built on text-to-image generation, to avoid the labor-intensive foreground extraction of prior two-stage methods. It adds Cross-Attention Refinement (CAR), which uses the diffusion model's cross-attention map to refine bounding box annotations, and Background Occlusion Modeling (BOM), which models background occlusion in latent space. Experiments report a 1.2% mAP improvement over previous methods and better prohibited item detection across several X-ray datasets and detectors.