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 t...
详细信息
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 *** probability margin(PM)method is a promising approach to continuously and path-independently mea-suring such closeness between the example and decision ***,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 *** 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 ***-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 *** 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 ***-PM shares a negative correlation with data vulnerability:data with larger/smaller CL-PM is safer/riskier and should have a smaller/larger *** 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.
The stability and uniformity of solid electrolyte interphase(SEI)are critical for clarifying the origin of capacity fade and safety issues for lithium metal anodes(LMA).However,understanding the interplay of SEI heter...
详细信息
The stability and uniformity of solid electrolyte interphase(SEI)are critical for clarifying the origin of capacity fade and safety issues for lithium metal anodes(LMA).However,understanding the interplay of SEI heterogeneity and Li electrodeposition is limited by the coupling of complex electrochemistry and mechanics ***,the correlation between the SEI failure behavior and Li deposition morphology is investigated through a quantitative electrochemical-mechanical *** local deformation and stress of SEI during Li electrodeposition identify that the heterogeneous interface between different components first *** with the well-known mechanical strength,component uniformity plays the most important role in the initial SEI failure and uneven Li deposition,and a relative component uniformity(p>0.01)represents a proper balance to ensure the stability of the naturally heterogeneous ***,the component regulation of SEI via the designed electrolyte experimentally demonstrates that improving component uniformity benefits SEI stability and the uniform Li electrodeposition for LMA,thereby increasing the capacity by~20%after 300 *** fundamental understandings and proposed strategy can be not only used to guide the SEI optimization via the electrolyte regulation,but also extended to the rational designs of artificial SEI for high-performance LMA.
The accurate quantification of risk caused by uncertainty forms a crucial foundation for formulating the generation maintenance scheduling (GMS) of power systems. However, the probability distribution functions (PDFs)...
详细信息
In light of global aging and prevalent stroke-related hemiplegia, this study addresses challenges in robot-assisted Sit-to-Stand (STS) movements, a daily activity prone to falls. Supernumerary Robotic Legs (SRL) serve...
详细信息
As a crucial auxiliary technique in inertial navigation, scene matching has been widely applied in aircraft navigation and guidance. To enhance the adaptability and efficiency of scene matching algorithms in complex e...
详细信息
In the last decades,as a typical nonlinear system,active magnetic bearings(AMB) system has been widely applied in manufacturing systems.A sliding mode control(SMC) scheme for the AMB system is proposed with the distur...
详细信息
ISBN:
(数字)9789887581536
ISBN:
(纸本)9781665482561
In the last decades,as a typical nonlinear system,active magnetic bearings(AMB) system has been widely applied in manufacturing systems.A sliding mode control(SMC) scheme for the AMB system is proposed with the disturbance observation of the linear extended state observer(LESO) in this *** chattering of the AMB system has been reduced by LESO-SMC by at least 60%.Sufficient BIBO(bounded input-bounded output) stability conditions of the closed-loop AMB system governed by the proposed LESO-SMC are derived by Lyapunov ***,experiments are conducted to verify the effectiveness and superiority of the proposed LESO-SMC than conventional SMC.
Social media is a platform for people to share their lives and interact with others. image sharing is an integral component. Privacy information will inevitably be compromised during the process of sharing whole photo...
详细信息
Compared to traditional area coverage algorithms, this paper proposes a re-plannable multi-agent coverage path planning algorithm to address issues such as low coverage rate of multiple agents in large-scale scenarios...
详细信息
Bokeh effect transformation is a novel task in computer vision and computational photography. It aims to convert bokeh effects from one camera lens to another. To this end, we introduce a new concept of blur ratio, wh...
详细信息
The instance segmentation of impacted teeth in the oral panoramic X-ray images is hotly ***,due to the complex structure,low contrast,and complex background of teeth in panoramic X-ray images,the task of instance segm...
详细信息
The instance segmentation of impacted teeth in the oral panoramic X-ray images is hotly ***,due to the complex structure,low contrast,and complex background of teeth in panoramic X-ray images,the task of instance segmentation is technically *** this study,the contrast between impacted Teeth and periodontal tissues such as gingiva,periodontalmembrane,and alveolar bone is low,resulting in fuzzy boundaries of impacted *** based on Teeth YOLACT is proposed to provide amore efficient and accurate solution for the segmentation of impacted teeth in oral panoramic X-ray ***,a Multi-scale Res-Transformer Module(MRTM)is *** the module,depthwise separable convolutions with different receptive fields are used to enhance the sensitivity of the model to lesion ***,the Vision Transformer is integrated to improve the model’s ability to perceive global ***,the Context Interaction-awareness Module(CIaM)is designed to fuse deep and shallow *** deep semantic features guide the shallow spatial ***,the shallow spatial features are embedded into the deep semantic features,and the cross-weighted attention mechanism is used to aggregate the deep and shallow features efficiently,and richer context information is ***,the Edge-preserving perceptionModule(E2PM)is designed to enhance the teeth edge *** first-order differential operator is used to get the tooth edge weight,and the perception ability of tooth edge features is *** shallow spatial feature is fused by linear mapping,weight concatenation,and matrix multiplication operations to preserve the tooth edge ***,comparison experiments and ablation experiments are conducted on the oral panoramic X-ray image *** results show that the APdet,APseg,ARdet,ARseg,mAPdet,and mAPseg indicators of the proposed model are 89.9%,91.9%,77.4%,77.6%,72.8%,and 73.5%,*** study further verifies the a
暂无评论