Exploring Endogenous Shift for Cross-domain Detection: A Large-scale Benchmark and Perturbation Suppression Network

Tao, Renshuai; Li, Hainan; Wang, Tianbo; Wei, Yanlu; Ding, Yifu; Jin, Bowei; Zhi, Hongping; Liu, Xianglong; Liu, Aishan

doi:10.1109/cvpr52688.2022.02051

Cited by 23 publications

(3 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, due to privacy policies, many X-ray baggage image datasets cannot be publicly released. To the best of our knowledge, the five current datasets used for X-ray prohibited detection are GDXay [ 31 ], SIXray [ 32 ], OPIXray [ 33 ], HiXray [ 34 ], and EDS [ 35 ].…”

Section: Related Workmentioning

confidence: 99%

Fine-YOLO: A Simplified X-ray Prohibited Object Detection Network Based on Feature Aggregation and Normalized Wasserstein Distance

Zhou,

Cao,

et al. 2024

Sensors

View full text Add to dashboard Cite

X-ray images typically contain complex background information and abundant small objects, posing significant challenges for object detection in security tasks. Most existing object detection methods rely on complex networks and high computational costs, which poses a challenge to implement lightweight models. This article proposes Fine-YOLO to achieve rapid and accurate detection in the security domain. First, a low-parameter feature aggregation (LPFA) structure is designed for the backbone feature network of YOLOv7 to enhance its ability to learn more information with a lighter structure. Second, a high-density feature aggregation (HDFA) structure is proposed to solve the problem of loss of local details and deep location information caused by the necked feature fusion network in YOLOv7-Tiny-SiLU, connecting cross-level features through max-pooling. Third, the Normalized Wasserstein Distance (NWD) method is employed to alleviate the convergence complexity resulting from the extreme sensitivity of bounding box regression to small objects. The proposed Fine-YOLO model is evaluated on the EDS dataset, achieving a detection accuracy of 58.3% with only 16.1 M parameters. In addition, an auxiliary validation is performed on the NEU-DET dataset, the detection accuracy reaches 73.1%. Experimental results show that Fine-YOLO is not only suitable for security, but can also be extended to other inspection areas.

show abstract

Section: Related Workmentioning

confidence: 99%

Fine-YOLO: A Simplified X-ray Prohibited Object Detection Network Based on Feature Aggregation and Normalized Wasserstein Distance

Zhou,

Cao,

et al. 2024

Sensors

View full text Add to dashboard Cite

show abstract

“…In addition, large-scale MDD datasets collected from multisite suffer from shifts, including exogenous shift caused by imaging at different resolutions, and endogenous shift caused by internal factors such as equipment hardware parameters and the degree of machine aging. These shifts can cause large differences in the spatial distribution between the training and test sets, which can lead to a sharp drop in model performance [24]. And most studies have proposed ideas to solve the exogenous shift with single site as a domain [13], and few have focused on the endogenous shift.…”

Section: Introductionmentioning

confidence: 99%

Cross-Domain Identification of Multisite Major Depressive Disorder Using End-to-End Brain Dynamic Attention Network

Yuan,

Chen,

Ding

et al. 2024

IEEE Trans. Neural Syst. Rehabil. Eng.

View full text Add to dashboard Cite

Objectives: Establishing objective and quantitative imaging markers at individual level can assist in accurate diagnosis of Major Depressive Disorder (MDD). However, the clinical heterogeneity of MDD and the shift to multisite data decreased identification accuracy. To address these issues, the Brain Dynamic Attention Network (BDANet) is innovatively proposed, and analyzed bimodal scans from 2055 participants of the Rest-meta-MDD consortium. Methods: The end-to-end BDANet contains two crucial components. The Dynamic BrainGraph Generator dynamically focuses and represents topological relationships between Regions of Interest, overcoming limitations of static methods. The Ensemble Classifier is constructed to obfuscate domain sources to achieve inter-domain alignment. Finally, BDANet dynamically generates sample-specific brain graphs by downstream recognition tasks. Results: The proposed BDANet achieved an accuracy of 81.6%. The regions with high attribution for classification were mainly located in the insula, cingulate cortex and auditory cortex. The level of brain connectivity in p24 region was negatively correlated (p<0.05) with the severity of MDD. Additionally, sex differences in connectivity strength were observed in specific brain regions and functional subnetworks (p<0.05 or p<0.01). Conclusions and Significance: These findings based on a large multisite dataset support the conclusion that BDANet can better solve the problem of the clinical heterogeneity of MDD and the shift of multisite data. It also illustrates the potential utility of BDANet for personalized accurate identification, treatment and intervention of MDD.

show abstract

“…Recently, deep learning has been introduced into safety-critical scenarios such as X-ray security inspection in public transportation hubs (e.g., airports). In this scenario [32,40,42,47], deep-learning-based detectors are utilized to assist inspectors in identifying both the presence and location of prohibited items (e.g., pistols and knives) during X-ray scanning. This approach significantly reduces the amount of human labor required and helps to protect the public from severe risks.…”

Section: Introductionmentioning

confidence: 99%

X-Adv: Physical Adversarial Object Attacks against X-ray Prohibited Item Detection

Liu¹,

Guo²,

Wang³

et al. 2023

Preprint

View full text Add to dashboard Cite

Adversarial attacks are valuable for evaluating the robustness of deep learning models. Existing attacks are primarily conducted on the visible light spectrum (e.g., pixel-wise texture perturbation). However, attacks targeting texture-free X-ray images remain underexplored, despite the widespread application of X-ray imaging in safety-critical scenarios such as the X-ray detection of prohibited items. In this paper, we take the first step toward the study of adversarial attacks targeted at X-ray prohibited item detection, and reveal the serious threats posed by such attacks in this safety-critical scenario. Specifically, we posit that successful physical adversarial attacks in this scenario should be specially designed to circumvent the challenges posed by color/texture fading and complex overlapping. To this end, we propose X -Adv to generate physically printable metals that act as an adversarial agent capable of deceiving X-ray detectors when placed in luggage. To resolve the issues associated with color/texture fading, we develop a differentiable converter that facilitates the generation of 3D-printable objects with adversarial shapes, using the gradients of a surrogate model rather than directly generating adversarial textures. To place the printed 3D adversarial objects in luggage with complex overlapped instances, we design a policy-based reinforcement learning strategy to find locations eliciting strong attack performance in worst-case scenarios whereby the prohibited items are heavily occluded by other items. To verify the effectiveness of the proposed X -Adv, we conduct extensive experiments in both the digital and the physical world (employing a commercial X-ray security inspection system for the latter case). Furthermore, we present the physical-world X-ray adversarial attack dataset XAD. We hope this paper will draw more attention to the potential threats targeting safetycritical scenarios. Our codes and XAD dataset are available at https://github.com/DIG-Beihang/X-adv.

show abstract

Exploring Endogenous Shift for Cross-domain Detection: A Large-scale Benchmark and Perturbation Suppression Network

Cited by 23 publications

References 41 publications

Fine-YOLO: A Simplified X-ray Prohibited Object Detection Network Based on Feature Aggregation and Normalized Wasserstein Distance

Fine-YOLO: A Simplified X-ray Prohibited Object Detection Network Based on Feature Aggregation and Normalized Wasserstein Distance

Cross-Domain Identification of Multisite Major Depressive Disorder Using End-to-End Brain Dynamic Attention Network

X-Adv: Physical Adversarial Object Attacks against X-ray Prohibited Item Detection

Contact Info

Product

Resources

About