Meta-Transfer Learning Driven Tensor-Shot Detector for the Autonomous Localization and Recognition of Concealed Baggage Threats

Abstract

Screening baggage against potential threats has become one of the prime aviation security concerns all over the world, where manual detection of prohibited items is a time-consuming and hectic process. Many researchers have developed autonomous systems to recognize baggage threats using security X-ray scans. However, all of these frameworks are vulnerable against screening cluttered and concealed contraband items. Furthermore, to the best of our knowledge, no framework possesses the capacity to recognize baggage threats across multiple scanner specifications without an explicit retraining process. To overcome this, we present a novel meta-transfer learning-driven tensor-shot detector that decomposes the candidate scan into dual-energy tensors and employs a meta-one-shot classification backbone to recognize and localize the cluttered baggage threats. In addition, the proposed detection framework can be well-generalized to multiple scanner specifications due to its capacity to generate object proposals from the unified tensor maps rather than diversified raw scans. We have rigorously evaluated the proposed tensor-shot detector on the publicly available SIXray and GDXray datasets (containing a cumulative of 1,067,381 grayscale and colored baggage X-ray scans). On the SIXray dataset, the proposed framework achieved a mean average precision (mAP) of 0.6457, and on the GDXray dataset, it achieved the precision and F1 score of 0.9441 and 0.9598, respectively. Furthermore, it outperforms state-of-the-art frameworks by 8.03% in terms of mAP, 1.49% in terms of precision, and 0.573% in terms of F1 on the SIXray and GDXray dataset, respectively.

Few-Shot Adaptive Detection of Objects of Concern Using Generative Models with Negative Retraining

“…The GANomaly and Skip-GANomaly auto-encoders [22], [23] perform OoD detection and are tested on the University Baggage Anomaly (UBA) and Full Firearm Operational Benign (FFOB) datasets. The Meta-Transfer Learning model [24] decomposes X-ray images into energy tensors and then performs few-shot classification [25], [26]. The Transfer Learning CNN model [27] evaluates whether inter-scanner generalisation exists over a multiple class detection problem.…”

“…Benchmarks. For SIXray, we use OoD detection benchmarks, [17], [24], [27]. For CIFAR-10 data, we use [28].…”

“…Table II shows the performance of REFGAN compared to benchmarks [17], [27]. Table III presents the mean performance of REFGAN compared to [17], [24], [27].…”

Deep Learning for Object Detection, Classification and Tracking in Industry Applications

“…Wang et al [7] introduced a domain-specific benchmark dataset, called AgriPest, for tiny wild pest recognition and detection, providing researchers and communities with a standard large-scale dataset of wild pest images and annotations, as well as evaluation procedures. A meta-transfer learning-driven tensor-shot detector was presented [8] that decomposes the candidate scans into dual-energy tensors and employs a meta-one-shot classification backbone to recognize and localize cluttered baggage threats. The tensor-shot detector was evaluated on the publicly available SIXray and GDXray datasets.…”

Deep Feature Fusion Based Dual Branch Network for X-ray Security Inspection Image Classification

“…This work provides an authoritative verification benchmark for the related research about X-ray security inspection images. In recent years, many studies have been conducted with the adoption of this dataset [22][23][24][25]. Specific to object occlusion in X-ray security inspection image, research [26] proposed a dataset named occluded prohibited items X-ray (OPIXray) image benchmark.…”