Chen, Ruikang;
Yan, Yan;
Xue, Jing-Hao;
Lu, Yang;
Wang, Hanzi;
(2024)
Augmentation Matters: A Mix-Paste Method for X-Ray Prohibited Item Detection under Noisy Annotations.
IEEE Transactions on Information Forensics and Security
, 20
234 -248.
10.1109/tifs.2024.3516546.
Preview |
Text
RuikangChen-TIFS-2024.pdf - Accepted Version Download (2MB) | Preview |
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 .
| Type: | Article |
|---|---|
| Title: | Augmentation Matters: A Mix-Paste Method for X-Ray Prohibited Item Detection under Noisy Annotations |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.1109/tifs.2024.3516546 |
| Publisher version: | https://doi.org/10.1109/tifs.2024.3516546 |
| Language: | English |
| Additional information: | This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. |
| Keywords: | Object detection, noisy annotation, data augmentation, X-ray prohibited item detection |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences > Dept of Statistical Science |
| URI: | https://discovery-pp.ucl.ac.uk/id/eprint/10202705 |
Archive Staff Only
 |
View Item |
