Saved in:
Bibliographic Details
Main Authors: Heidari, Omid Reza, Wang, Yang, Zuo, Xinxin
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.02696
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915648821526528
author Heidari, Omid Reza
Wang, Yang
Zuo, Xinxin
author_facet Heidari, Omid Reza
Wang, Yang
Zuo, Xinxin
contents Domain adaptation in object detection is critical for real-world applications where distribution shifts degrade model performance. Security X-ray imaging presents a unique challenge due to variations in scanning devices and environmental conditions, leading to significant domain discrepancies. To address this, we apply ALDI++, a domain adaptation framework that integrates self-distillation, feature alignment, and enhanced training strategies to mitigate domain shift effectively in this area. We conduct extensive experiments on the EDS dataset, demonstrating that ALDI++ surpasses the state-of-the-art (SOTA) domain adaptation methods across multiple adaptation scenarios. In particular, ALDI++ with a Vision Transformer for Detection (ViTDet) backbone achieves the highest mean average precision (mAP), confirming the effectiveness of transformer-based architectures for cross-domain object detection. Additionally, our category-wise analysis highlights consistent improvements in detection accuracy, reinforcing the robustness of the model across diverse object classes. Our findings establish ALDI++ as an efficient solution for domain-adaptive object detection, setting a new benchmark for performance stability and cross-domain generalization in security X-ray imagery.
format Preprint
id arxiv_https___arxiv_org_abs_2512_02696
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ALDI-ray: Adapting the ALDI Framework for Security X-ray Object Detection
Heidari, Omid Reza
Wang, Yang
Zuo, Xinxin
Computer Vision and Pattern Recognition
Machine Learning
Domain adaptation in object detection is critical for real-world applications where distribution shifts degrade model performance. Security X-ray imaging presents a unique challenge due to variations in scanning devices and environmental conditions, leading to significant domain discrepancies. To address this, we apply ALDI++, a domain adaptation framework that integrates self-distillation, feature alignment, and enhanced training strategies to mitigate domain shift effectively in this area. We conduct extensive experiments on the EDS dataset, demonstrating that ALDI++ surpasses the state-of-the-art (SOTA) domain adaptation methods across multiple adaptation scenarios. In particular, ALDI++ with a Vision Transformer for Detection (ViTDet) backbone achieves the highest mean average precision (mAP), confirming the effectiveness of transformer-based architectures for cross-domain object detection. Additionally, our category-wise analysis highlights consistent improvements in detection accuracy, reinforcing the robustness of the model across diverse object classes. Our findings establish ALDI++ as an efficient solution for domain-adaptive object detection, setting a new benchmark for performance stability and cross-domain generalization in security X-ray imagery.
title ALDI-ray: Adapting the ALDI Framework for Security X-ray Object Detection
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2512.02696