从三维Mesh数据中分割建筑物立面以识别对象,是三维场景理解的关键,但现有方法多依赖高成本的精细标注数据。针对该问题,提出了一种半监督学习方法,引入一种基于对比学习和一致性正则化的半监督语义分割(semi-supervised semantic segme...从三维Mesh数据中分割建筑物立面以识别对象,是三维场景理解的关键,但现有方法多依赖高成本的精细标注数据。针对该问题,提出了一种半监督学习方法,引入一种基于对比学习和一致性正则化的半监督语义分割(semi-supervised semantic segmentation based on contrastive learning and consistency regularization,SS_CC)方法,用于分割三维Mesh数据的建筑物立面。在SS_CC方法中,改进后的对比学习模块利用正负样本之间的类可分性,能够更有效地利用类特征信息;提出的基于特征空间的一致性正则化损失函数,从挖掘全局特征的角度增强了对所提取建筑物立面特征的鉴别力。实验结果表明,所提出的SS_CC方法在F1分数、mIoU指标上优于当前一些主流方法,且在建筑物的墙面和窗户上的分割效果相对更好。展开更多
Separating oil/water mixtures via superhydrophobic stainless steel mesh(SSM)is a kind of efficient methods of treating oily wastewater,and the superhydrophobic SSM with a low cost,simple fabrication process and robust...Separating oil/water mixtures via superhydrophobic stainless steel mesh(SSM)is a kind of efficient methods of treating oily wastewater,and the superhydrophobic SSM with a low cost,simple fabrication process and robust usability remains a challenge.Herein,urushiol-based benzoxazine(U-D)with a strong substrate adhesion and low surface free energy was used to anchor SiO_(2) particles on the SSM surface to obtain a durable superhydrophobic SSM(PU-D/SiO_(2)/SSM)through a simple dip-coating process,meanwhile,epoxy resin was also introduced to further improve the adhesion between coating and SSM.PU-D/SiO_(2)/SSM could successfully separate various immiscible oil-water mixtures with a separation efficiency of over 96%and a flux up to 27100 L/m^(2) h only by gravity,respectively.Especially,the modified SSM could effectively remove water from water-in-oil emulsion with a separation efficiency of 99.7%.Moreover,PU-D/SiO_(2)/SSM had an outstanding reusability,whose water contact angle and separation efficiency only slightly decreased after 20 cycles of separating oil/water mixture.In addition,the modified SSM also displayed a satisfactory abrasion resistance,chemical stability and self-cleaning property.Thereby,the robust PU-D/SiO_(2)/SSM prepared by cheap raw materials and facile dip-coating method exhibits a high potential for separating oil/water mixtures.展开更多
Mechanically durable transparent electrodes are essential for achieving long-term stability in flexible optoelectronic devices.Furthermore,they are crucial for applications in the fields of energy,display,healthcare,a...Mechanically durable transparent electrodes are essential for achieving long-term stability in flexible optoelectronic devices.Furthermore,they are crucial for applications in the fields of energy,display,healthcare,and soft robotics.Conducting meshes represent a promising alternative to traditional,brittle,metal oxide conductors due to their high electrical conductivity,optical transparency,and enhanced mechanical flexibility.In this paper,we present a simple method for fabricating an ultra-transparent conducting metal oxide mesh electrode using selfcracking-assisted templates.Using this method,we produced an electrode with ultra-transparency(97.39%),high conductance(Rs=21.24Ωsq^(−1)),elevated work function(5.16 eV),and good mechanical stability.We also evaluated the effectiveness of the fabricated electrodes by integrating them into organic photovoltaics,organic light-emitting diodes,and flexible transparent memristor devices for neuromorphic computing,resulting in exceptional device performance.In addition,the unique porous structure of the vanadium-doped indium zinc oxide mesh electrodes provided excellent flexibility,rendering them a promising option for application in flexible optoelectronics.展开更多
文摘从三维Mesh数据中分割建筑物立面以识别对象,是三维场景理解的关键,但现有方法多依赖高成本的精细标注数据。针对该问题,提出了一种半监督学习方法,引入一种基于对比学习和一致性正则化的半监督语义分割(semi-supervised semantic segmentation based on contrastive learning and consistency regularization,SS_CC)方法,用于分割三维Mesh数据的建筑物立面。在SS_CC方法中,改进后的对比学习模块利用正负样本之间的类可分性,能够更有效地利用类特征信息;提出的基于特征空间的一致性正则化损失函数,从挖掘全局特征的角度增强了对所提取建筑物立面特征的鉴别力。实验结果表明,所提出的SS_CC方法在F1分数、mIoU指标上优于当前一些主流方法,且在建筑物的墙面和窗户上的分割效果相对更好。
基金Funded by the National Natural Science Foundation of China(No.22165019)。
文摘Separating oil/water mixtures via superhydrophobic stainless steel mesh(SSM)is a kind of efficient methods of treating oily wastewater,and the superhydrophobic SSM with a low cost,simple fabrication process and robust usability remains a challenge.Herein,urushiol-based benzoxazine(U-D)with a strong substrate adhesion and low surface free energy was used to anchor SiO_(2) particles on the SSM surface to obtain a durable superhydrophobic SSM(PU-D/SiO_(2)/SSM)through a simple dip-coating process,meanwhile,epoxy resin was also introduced to further improve the adhesion between coating and SSM.PU-D/SiO_(2)/SSM could successfully separate various immiscible oil-water mixtures with a separation efficiency of over 96%and a flux up to 27100 L/m^(2) h only by gravity,respectively.Especially,the modified SSM could effectively remove water from water-in-oil emulsion with a separation efficiency of 99.7%.Moreover,PU-D/SiO_(2)/SSM had an outstanding reusability,whose water contact angle and separation efficiency only slightly decreased after 20 cycles of separating oil/water mixture.In addition,the modified SSM also displayed a satisfactory abrasion resistance,chemical stability and self-cleaning property.Thereby,the robust PU-D/SiO_(2)/SSM prepared by cheap raw materials and facile dip-coating method exhibits a high potential for separating oil/water mixtures.
基金supported by a National Research Foundation of Korea(NRF)grant(No.2016R1A3B 1908249)funded by the Korean government.
文摘Mechanically durable transparent electrodes are essential for achieving long-term stability in flexible optoelectronic devices.Furthermore,they are crucial for applications in the fields of energy,display,healthcare,and soft robotics.Conducting meshes represent a promising alternative to traditional,brittle,metal oxide conductors due to their high electrical conductivity,optical transparency,and enhanced mechanical flexibility.In this paper,we present a simple method for fabricating an ultra-transparent conducting metal oxide mesh electrode using selfcracking-assisted templates.Using this method,we produced an electrode with ultra-transparency(97.39%),high conductance(Rs=21.24Ωsq^(−1)),elevated work function(5.16 eV),and good mechanical stability.We also evaluated the effectiveness of the fabricated electrodes by integrating them into organic photovoltaics,organic light-emitting diodes,and flexible transparent memristor devices for neuromorphic computing,resulting in exceptional device performance.In addition,the unique porous structure of the vanadium-doped indium zinc oxide mesh electrodes provided excellent flexibility,rendering them a promising option for application in flexible optoelectronics.
