In recent years, automatic detection of threats in X-ray baggage has become important in security inspection. However, the training of threat detectors often requires extensive, well-annotated images, which are hard to procure, especially for rare contraband items. In this paper, a few-shot SVM-constraint threat detection model, named FSVM is proposed, which aims at detecting unseen contraband items with only a small number of labeled samples. Rather than simply finetuning the original model, FSVM embeds a derivable SVM layer to back-propagate the supervised decision information into the former layers. A combined loss function utilizing SVM loss is also created as the additional constraint. We have evaluated FSVM on the public security baggage dataset SIXray, performing experiments on 10-shot and 30-shot samples under three class divisions. Experimental results show that compared with four common few-shot detection models, FSVM has the highest performance and is more suitable for complex distributed datasets (e.g., X-ray parcels).

Due to the unique imaging mechanism of synthetic aperture radar (SAR), which leads to a discrete state of aircraft targets in images, its detection performance is vulnerable to the influence of complex ground objects. Although existing deep learning detection algorithms show good performance, they generally use a feature pyramid neck design and large backbone network, which reduces the detection efficiency to some extent. To address these problems, we propose a simple and efficient attention network (SEAN) in this paper, which takes YOLOv5s as the baseline. First, we shallow the depth of the backbone network and introduce a structural re-parameterization technique to increase the feature extraction capability of the backbone. Second, the neck architecture is designed by using a residual dilated module (RDM), a low-level semantic enhancement module (LSEM), and a localization attention module (LAM), substantially reducing the number of parameters and computation of the network. The results on the Gaofen-3 aircraft target dataset show that this method achieves 97.7% AP at a speed of 83.3 FPS on a Tesla M60, exceeding YOLOv5s by 1.3% AP and 8.7 FPS with 40.51% of the parameters and 86.25% of the FLOPs.

This paper proposes an information enhancement network based on self-supervised learning (SEL-Net) for runway area detection. During the self-supervised learning phase, the distinctive attributes of PolSAR multi-channel data are fully harnessed to enhance the generated pretrained model’s focus on airport runway areas. During the detection phase, this paper presents an improved U-Net detection network. Edge Feature Extraction Modules (EEM) are integrated into the encoder and skip connection sections, while Semantic Information Transmission Modules (STM) are embedded into the decoder section. Furthermore, improvements have been applied to the network’s upsampling and downsampling architectures. Experimental results demonstrate that the proposed SEL-Net effectively addresses the issues of high false alarms and runway integrity, achieving a superior detection performance.