Illicit object detection in X-ray images using Vision Transformers
This addresses the problem of automating security screening to reduce human burden, but it is incremental as it applies existing methods to a domain-specific task.
The paper tackled illicit object detection in X-ray images by evaluating Vision Transformers and hybrid architectures, finding that the DINO Transformer detector achieved high accuracy with limited data, YOLOv8 offered real-time performance, and the NextViT backbone was effective.
Illicit object detection is a critical task performed at various high-security locations, including airports, train stations, subways, and ports. The continuous and tedious work of examining thousands of X-ray images per hour can be mentally taxing. Thus, Deep Neural Networks (DNNs) can be used to automate the X-ray image analysis process, improve efficiency and alleviate the security officers' inspection burden. The neural architectures typically utilized in relevant literature are Convolutional Neural Networks (CNNs), with Vision Transformers (ViTs) rarely employed. In order to address this gap, this paper conducts a comprehensive evaluation of relevant ViT architectures on illicit item detection in X-ray images. This study utilizes both Transformer and hybrid backbones, such as SWIN and NextViT, and detectors, such as DINO and RT-DETR. The results demonstrate the remarkable accuracy of the DINO Transformer detector in the low-data regime, the impressive real-time performance of YOLOv8, and the effectiveness of the hybrid NextViT backbone.