|
|
|
题名
|
作者
|
年代
|
出处
|
被引量
|
| 1 | Progress of study on hydrology water resource and waterenvironment显示文摘 | Li Zuoyong | 2002 | Journal of Sichuan University: Engineering Science Edition2002，34，2： | 1 |
| 2 | Image retrieval based on micro-structure descriptor 显示文摘 | GUANGHAI LIU ZUOYONG LI LEI ZHANG | 2011 | Pattern Recognition2011，44，9： | 1 |
| 3 | Statistical thresholding method for infrared images显示文摘 | Li Zuoyong Liu Chuancai Liu Guanghai | 2011 | Pattern Analysis and Applications2011，14，： | 1 |
| 4 | Modified local entropy-based transition region extraction and thresholding 显示文摘 | Li Zuoyong Zhang David Yong Xu | 2011 | Applied Soft Computing2011，11，8： | 1 |
| 5 | Gray level difference-based transition region extraction and thresholding显示文摘 | Li Zuoyong Liu Chuaneai | 2009 | Computers & Electrical En- gineering2009，35，5： | 1 |
| 6 | Image retrieval based on multi-structure descriptor显示文摘 | Liu Guanghai Li Zuoyong Zhang Lei | 2011 | Pattern Reeognition2011，44，9： | 1 |
| 7 | Modified local enlropy based transilion region extraction and thresholding显示文摘 | Li Zuoyong Zhang David | 2011 | Applied Sofl Computing2011，11，8： | 1 |
| 8 | A new feature-preserving mesh-smoothing algorithm 显示文摘 | Li Zhong Ma Lizhuang Jin Xiaogang Zheng Zuoyong | 2009 | The Visual Computer2009，25，2： | 1 |
| 9 | The impact of reflux ratio on rectification column theoretical plate number显示文摘 | WANG Jiayang LI Zuoyong ZHANG Bi | 2012 | Advanced Materials Research2012，，418419420： | 1 |
| 10 | Modified local entropy-based transition region extraction and thresholding 显示文摘 | LI Zuoyong ZHANG D XU Yong | 2011 | Applied Soft Computing2011，11，： | 1 |
| 11 | Multi-strategy adaptive particle swarm optimization for numerical optimization显示文摘 | Kezong Tang Zuoyong Li Limin Luo Bingxiang Liu | 2015 | Engineering Applications of Artificial Intelligen2015，，： | 1 |
| 12 | A novelstatistical image thresholding method 显示文摘 | LI Zuoyong LIU Chuncai LIU Guanghai | 2010 | AEU - Interna-tional Journal of Electronics and Communications2010，64，12： | 1 |
| 13 | A technique of reconstructing field for measuring sound reflection coefficients at arbitrary angles of incidence显示文摘An improved reconstructing field method for measuring sound reflection coefficient of a large impedance surface at arbitrary incident angles is proposed in this paper. In order to get the reflection coefficient by the Spatial Transformation of Sound Fields (STSF), the complex pressure on two parallel planes near by the material surface or the reflection surface must be measured. By the acoustic intensity measurement, the phases of complex pressure on two parallel planes are given. The results of the numerical simulations are shown that the error due to the finite size of the measurement area, and it may be reduced by using a dipole sound source. | HE Yuanan, LI Rui, HE Zuoyong (Harbin Engineering University Harbin 150001) | 2001 | Chinese Journal of Acoustics2001，20，4： | 0 |
| 14 | Instance Reweighting Adversarial Training Based on Confused Label显示文摘Reweighting adversarial examples during training plays an essential role in improving the robustness of neural networks,which lies in the fact that examples closer to the decision boundaries are much more vulnerable to being attacked and should be given larger weights.The probability margin(PM)method is a promising approach to continuously and path-independently mea-suring such closeness between the example and decision boundary.However,the performance of PM is limited due to the fact that PM fails to effectively distinguish the examples having only one misclassified category and the ones with multiple misclassified categories,where the latter is closer to multi-classification decision boundaries and is supported to be more critical in our observation.To tackle this problem,this paper proposed an improved PM criterion,called confused-label-based PM(CL-PM),to measure the closeness mentioned above and reweight adversarial examples during training.Specifi-cally,a confused label(CL)is defined as the label whose prediction probability is greater than that of the ground truth label given a specific adversarial example.Instead of considering the discrepancy between the probability of the true label and the probability of the most misclassified label as the PM method does,we evaluate the closeness by accumulating the probability differences of all the CLs and ground truth label.CL-PM shares a negative correlation with data vulnerability:data with larger/smaller CL-PM is safer/riskier and should have a smaller/larger weight.Experiments demonstrated that CL-PM is more reliable in indicating the closeness regarding multiple misclassified categories,and reweighting adversarial training based on CL-PM outperformed state-of-the-art counterparts. | Zhicong Qiu Xianmin Wang Huawei Ma Songcao Hou Jing Li Zuoyong Li | 2023 | Intelligent Automation & Soft Computing2023，37，8： | 0 |
您所在的机构暂未开通此部分的功能，请联系管理员