Self supervised method localizes any object in x ray scans
Localize Any Object in X-Ray Security Scans without Human Annotation
Computer Vision and Pattern Recognition
Summary
Detecting objects in X-ray security images is hard because these images look very different from ordinary photos, and expert labels are rare. The authors developed a way to teach a model to find any object in these scans without needing human-labeled examples. They create synthetic training data by combining real image bits and use a step-by-step approach to handle more crowded and overlapping objects. Their method improved detection accuracy across several X-ray test sets, all without any human annotations.
What this means in practice
- •For security screening teams: Improve detection of suspicious items in crowded X-ray luggage scans without needing extensive expert annotations.
- •For automated inspection system developers: Create more robust general object localization models tailored for X-ray images using synthetic data and self-supervised training.
Authors
Yaqi Cai, Mingxuan Liu, Lorenzo Vaquero, Ning Wang, Nan Pu, Feng Xue, Elisa Ricci, Nicu Sebe
Abstract
Universal object localization in X-ray security inspection is critical for automated threat detection in safety-critical venues. However, unlike everyday RGB images that dominate web-scale visual data, X-ray scans exhibit distinct color patterns, ambiguous boundaries, and compositional structures caused by volumetric superposition. These gaps hinder the direct zero-shot transfer of dense perception foundation models trained on web-scale RGB data. Moreover, annotated X-ray data is scarce and requires expert labeling, limiting both the training of generalizable X-ray native models and the adaptation of RGB foundation models for X-ray data via fine-tuning. Given these challenges, the bright promise of highly generalizable perception models, enabled by data scaling laws in the RGB domain, remains largely out of reach for X-ray inspection. To this end, we introduce LAO-X, a self-supervised adaptation framework that Locates Any Object in X-ray scans using diverse synthesized image--annotation pairs with granularity-aware supervision. LAO-X first designs a saliency-guided X-ray object mining module to separate diverse object instances, which are then used for physics-guided synthesis in the absorbance domain. LAO-X further incorporates an occlusion-controlled curriculum strategy to fine-tune a Segment Anything Model 2 (SAM2) localizer, progressively adapting it to X-ray scans with increasing object counts and overlap levels. Experiments on six X-ray benchmarks show that LAO-X substantially improves category-agnostic localization, achieving 2\% to 23\% mAP gains over SAM2 and X-ray specific baselines in heavily cluttered scenarios, entirely without human-annotated labels.