Zhaoge Liu

Zhaoge Liu

Auto-generated profile, based on publicly available information

Zhaoge Liu

Huazhong Univ Sci & Technol, State Key Lab Digital Mfg Equipment & Technol, Wuhan 430074, Hubei, Peoples R China

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 February 2023 in IEEE Transactions on Industrial Informatics
Verified
Journal Article
Closed access
YCYunkang Cao
Yunkang Cao
XXXiaohao Xu
Xiaohao Xu
ZLZhaoge Liu
Zhaoge Liu
Weiming ShenWeiming Shen
Weiming Shen
Most unsupervised image anomaly localization methods suffer from overgeneralization because of the high generalization abilities of convolutional neural networks, leading to unreliable predictions. To mitigate the overgeneralization, this article proposes to collaboratively optimize normal and abnormal feature distributions with the assistance of synthetic anomalies, namely collaborative discrepancy optimization (CDO). CDO introduces a margin optimization module and an overlap optimization module to optimize the two key factors determining the localization performance, i.e., the margin and the overlap between the discrepancy distributions (DDs) of normal and abnormal samples. With CDO, a large margin and a small overlap between normal and abnormal DDs are obtained, and the prediction reliability is boosted. Experiments on MVTec2D and MVTec3D show that CDO effectively mitigates the overgeneralization and achieves great anomaly localization performance with real-time computation efficiency. A real-world automotive plastic parts inspection application further demonstrates the capability of the proposed CDO.

12 August 2024 in Knowledge-Based Systems
Verified
Journal Article
Closed access
ZLZhaoge Liu
Zhaoge Liu
XXXiaohao Xu
Xiaohao Xu
YCYunkang Cao
Yunkang Cao
Weiming ShenWeiming Shen
Weiming Shen

1 June 2016
Verified
Conference Paper
Closed access
XLXiangyang Li
Xiangyang Li
GLGen Li
Gen Li
ZLZhaoge Liu
Zhaoge Liu
Risk communication is an important component of food safety analysis framework and the key factor of cultivating public risk perception, linking up with risk evaluation and forming food policies. There has been a lot of literatures to study the choosing basis, influencing factors, and forming processes of risk communication strategies. However, little of them focused on the automatically generating of the strategies. Aims at solving this problem, this paper proposes a mechanism of generating risk communication strategies which is based on the goals of risk communication. Firstly, proposing the innovate structure of risk communication strategies represented of framework and establishing the system of risk communication strategies. Then, based on the system, proposing the model of mechanism of generating risk communication strategies based on goals and stating the model in detail in the example of considering the lowest public opinion as the goal of risk communication. Finally, pointing the possible problems of the mechanism model and further research directions. This paper proposes an intellectualized procedure or method of generating risk communication strategies and provides aids to making the risk communication effective.