Augmentation Matters: A Mix-Paste Method for X-Ray Prohibited Item Detection Under Noisy Annotations

2025-01-03

IEEE Transactions on Information Forensics and Security

AI Summary

In X-ray prohibited item detection, annotation noise—arising from item occlusion and manifesting as erroneous class labels and bounding boxes—severely degrades model performance. To address this, we propose Mix-Paste, a label-aware mixed-patch augmentation method. Mix-Paste introduces a novel multi-tile pasting strategy grounded in class consistency, explicitly modeling the inherent overlap characteristics of X-ray imagery. Additionally, it incorporates an item-level large-loss suppression (LLS) mechanism to mitigate false-positive interference induced by augmentation. Evaluated on noisy X-ray datasets, Mix-Paste integrated with YOLOv8 significantly outperforms state-of-the-art methods, achieving substantial mAP gains. Its strong generalization capability is further validated on a synthetically noisy MS-COCO benchmark. The implementation is publicly available.

Technology Category

• Search and Optimization: Mixed Discrete/Continuous Search
• Computer Vision: Segmentation
• Constraint Satisfaction and Optimization: Mixed Discrete/Continuous Optimization

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Security and Privacy: Privacy-enhancing technologies
• Economics, Online Markets and Human Computation: Humans versus LLMs for data annotation and labeling

Abstract

Automatic X-ray prohibited item detection is vital for public safety. Existing deep learning-based methods all assume that the annotations of training X-ray images are correct. However, obtaining correct annotations is extremely hard if not impossible for large-scale X-ray images, where item overlapping is ubiquitous. As a result, X-ray images are easily contaminated with noisy annotations, leading to performance deterioration of existing methods. In this paper, we address the challenging problem of training a robust prohibited item detector under noisy annotations (including both category noise and bounding box noise) from a novel perspective of data augmentation, and propose an effective label-aware mixed patch paste augmentation method (Mix-Paste). Specifically, for each item patch, we mix several item patches with the same category label from different images and replace the original patch in the image with the mixed patch. In this way, the probability of containing the correct prohibited item within the generated image is increased. Meanwhile, the mixing process mimics item overlapping, enabling the model to learn the characteristics of X-ray images. Moreover, we design an item-based large-loss suppression (LLS) strategy to suppress the large losses corresponding to potentially positive predictions of additional items due to the mixing operation. We show the superiority of our method on X-ray datasets under noisy annotations. In addition, we evaluate our method on the noisy MS-COCO dataset to showcase its generalization ability. These results clearly indicate the great potential of data augmentation to handle noise annotations. The source code is released at https://github.com/wscds/Mix-Paste.

Problem

• X-ray image analysis
• Prohibited items detection
• Annotation errors

Innovation

• Mix-Paste
• X-ray contraband recognition
• imprecise annotation handling