Neural Networks (NN) are the functional unit of Deep Learning and are known to mimic the behavior of the human brain to solve complex data-driven problems. Whenever we train our own neural networks, we need to take ca...Neural Networks (NN) are the functional unit of Deep Learning and are known to mimic the behavior of the human brain to solve complex data-driven problems. Whenever we train our own neural networks, we need to take care of something called the generalization of the neural network. The performance of Artificial Neural Networks (ANN) mostly depends upon its generalization capability. In this paper, we propose an innovative approach to enhance the generalization capability of artificial neural networks (ANN) using structural redundancy. A novel perspective on handling input data prototypes and their impact on the development of generalization, which could improve to ANN architectures accuracy and reliability is described.展开更多
A native organ has heterogeneous structures, sirength, and cell components. It is a big challenge to fabricate organ prototypes with controllable shapes, strength, and cells. Herein, a hybrid method is developed to fa...A native organ has heterogeneous structures, sirength, and cell components. It is a big challenge to fabricate organ prototypes with controllable shapes, strength, and cells. Herein, a hybrid method is developed to fabricate organ prototypes with controlled cell deposition by integrating extrusion-based 3D printing, electrospinning, and 3D bioprinting. Multi-scale sheets were first fabricated by 3D printing and electrospinning;then, all the sheets were assembled into organ prototypes by sol-gel react io n duri ng bioprinting. With this method, macroscale structures fabricated by 3D printing ensure the customized structures and provide mechanical support, nanoscale structures fabricated by electrospinning offer a favorable environment for cell growth, and different types of cells with controllable densities are deposited in accurate locations by bioprinting. The results show that L929 mouse fibroblasts encapsulated in the structures exhibited over 90% survival within 10 days and maintai ned a high proliferation rate. Furthermore, the cells grew in spherical shapes first and then migrated to the nano scale fibers showing stretched morphology. Additionally, a branched vascular structure was successfully fabricated using the presented method. Compared with other methods, this strategy offers an easy way to simultancously realize the shape control, nanolibrous structures, and cell accurate deposition, which will have potemidi applications in tissue cngineering.展开更多
The effect of time and environment on the dimension precision and mass of LOM prototypes was experimentally investigated.It is to identify the stability of the dimension of LOM prototypes after forming.The results sho...The effect of time and environment on the dimension precision and mass of LOM prototypes was experimentally investigated.It is to identify the stability of the dimension of LOM prototypes after forming.The results show that the dimension and the mass tendency to grow,which is mainly caused by elastic recovery and moisture absorption and is characterized principally by the growth of Z dimension.Self restraint can be a significant factor to influence Z growth of LOM prototypes.展开更多
The prototype theory suggests that many metal concepts we have are really prototypes.It claims that children first learn words that are "basic" because they reflect aspects of the world,prototypes, which sta...The prototype theory suggests that many metal concepts we have are really prototypes.It claims that children first learn words that are "basic" because they reflect aspects of the world,prototypes, which stand out automatically from the rest of what they see.Basic level words should be taught first.展开更多
An in-depth study of bra pattern designs based on the existing bodice blocks was conducted to improve bra fit.The two popular bra prototypes,D's and Y's prototypes developed based on the existing bodice blocks...An in-depth study of bra pattern designs based on the existing bodice blocks was conducted to improve bra fit.The two popular bra prototypes,D's and Y's prototypes developed based on the existing bodice blocks for adult women,were first analyzed to understand their structural differences.Four bra samples were created and modified with respect to the standard shape and size of 75 B female mannequin breasts to compare the fit of the two bra prototypes.The fitness of these four bra samples was then tested on the mannequin and also on a real model of the same size.The examples demonstrated in the paper illustrate the principles and procedures for designing good-fit bras,and the bodice blocks using to develop bra prototypes in this study can also be replaced and widespread applied in other kind of bodice blocks in the future.展开更多
In order to reveal the appearance of the clothing prototype on the human body,the characteristics of the human body’s structure above the waist section were studied.Based on the experimental data of the fit prototype...In order to reveal the appearance of the clothing prototype on the human body,the characteristics of the human body’s structure above the waist section were studied.Based on the experimental data of the fit prototype,three-dimensional prototypes features were comparatively analyzed.And then objectively evaluating the relationship was conducted between the planar structure lines of different prototypes and the human body.The results showed that the prototypes analyzed basically conformed to the size of the human body.However,when they were worn on the human body,there were problems in the structure and forming.The main reason was that the side seam was skewed to different degrees.The results of this study provide reference for many practitioners to choose prototypes.展开更多
Cognitive linguistics is a new approach to language study, which can offer better explanation for language phenomena, and provide more theoretical instructions for English learning. In recent years, the prototype theo...Cognitive linguistics is a new approach to language study, which can offer better explanation for language phenomena, and provide more theoretical instructions for English learning. In recent years, the prototype theory, as the cornerstone of cognitive linguistics, has been employed in different research fields, such as phonology, syntax, semantics, English teaching, etc..This thesis attempts to review and discuss the researches done so far on semantics and categorization based on a cognitive theory -- the prototype theory.展开更多
In this paper we report the results of combined cycle- and life-aging and abuse tests carried out under severe conditions on Li<sub>4</sub>Ti<sub>5</sub>O<sub>12</sub>/LiFePO<sub...In this paper we report the results of combined cycle- and life-aging and abuse tests carried out under severe conditions on Li<sub>4</sub>Ti<sub>5</sub>O<sub>12</sub>/LiFePO<sub>4</sub> lithium-ion stacked prototypes using a PYR<sub>14</sub> FSI-LiTFSI ionic liquid electrolyte. No relevant degradation phenomena took place within ionic liquid electrolyte during prolonged inactivity period or overcharging. No fire/explosion or venting event as well as no gas development occurred during abuse tests, which led only to modest raise in temperature. Therefore, electrodes based on Li<sub>4</sub>Ti<sub>5</sub>O<sub>12</sub> and LiFePO<sub>4</sub> active materials can be favorably combined with non-volatile and non-flammable pyrrolidinium FSI ionic liquid electrolytes to realize highly safe lithium-ion battery systems.展开更多
Research on reconstructing imperfect faces is a challenging task.In this study,we explore a data-driven approach using a pre-trained MICA(MetrIC fAce)model combined with 3D printing to address this challenge.We propos...Research on reconstructing imperfect faces is a challenging task.In this study,we explore a data-driven approach using a pre-trained MICA(MetrIC fAce)model combined with 3D printing to address this challenge.We propose a training strategy that utilizes the pre-trained MICA model and self-supervised learning techniques to improve accuracy and reduce the time needed for 3D facial structure reconstruction.Our results demonstrate high accuracy,evaluated by the geometric loss function and various statistical measures.To showcase the effectiveness of the approach,we used 3D printing to create a model that covers facial wounds.The findings indicate that our method produces a model that fits well and achieves comprehensive 3D facial reconstruction.This technique has the potential to aid doctors in treating patients with facial injuries.展开更多
The 1.6GeV synchrotron of China Spallation Neutron Source(CSNS)project is a Rapid Cycling Synchrotron (RCS),which accelerates a high-intensity proton beam from 80MeV to 1.6GeV at a repetition rate of 25Hz.The RCS magn...The 1.6GeV synchrotron of China Spallation Neutron Source(CSNS)project is a Rapid Cycling Synchrotron (RCS),which accelerates a high-intensity proton beam from 80MeV to 1.6GeV at a repetition rate of 25Hz.The RCS magnet system consists of 24 dipole magnets(main dipoles),48 quadrupole magnets(main quadrupoles),16 sextupole magnets,some tune shift quadrupoles and corrector magnets.All the magnets are of large aperture for a high beam power of 0.1MW,one design issue is the fringe field at pole end.And the main dipoles and main quadrupoles work at 25Hz repetition rate,the eddy current is an additional issue.In this paper the magnet design of the two kinds of main magnets will be described.展开更多
无监督异常检测因只需要正常样本进行训练而被广泛应用于工业质检等领域。直接将现有的单类别异常检测方法应用到多类别异常检测中会导致性能显著下降,其中基于知识蒸馏的异常检测方法将预训练的教师模型关于正常样本的特征知识蒸馏到...无监督异常检测因只需要正常样本进行训练而被广泛应用于工业质检等领域。直接将现有的单类别异常检测方法应用到多类别异常检测中会导致性能显著下降,其中基于知识蒸馏的异常检测方法将预训练的教师模型关于正常样本的特征知识蒸馏到学生模型中,然而它们在多类别异常检测中存在无法保证学生模型只学习到正常样本知识的问题。文中提出一种基于反向知识蒸馏框架的无监督多类别异常检测方法(Prototype based Reverse Distillation,PRD),其通过Multi-class Normal Prototype模块和Sparse Prototype Recall训练策略来学习教师模型关于多类别正常样本特征的Prototype,并以此来过滤学生模型的输入特征,从而确保学生模型只学习到教师模型关于正常样本的特征知识。PRD在多种工业异常检测数据集上性能均超越了现有的SOTA方法,定性、定量和消融实验验证了PRD整体框架和内部模块的有效性。展开更多
Radio frequency(RF)cavities for advanced storage rings,also known as diffraction-limited storage rings,are under development.To this end,a competitive and promising approach involves normal-conducting continuous wave ...Radio frequency(RF)cavities for advanced storage rings,also known as diffraction-limited storage rings,are under development.To this end,a competitive and promising approach involves normal-conducting continuous wave technology.The design and preliminary test of a 499.654 MHz RF cavity for the Wuhan Advanced Light Source(WALS)based on specific beam parameters were conducted at the SSRF.Multi-objective evolutionary algorithms have been utilized to optimize RF properties,such as the power loss and power density,resulting in better performance in the continuous wave mode.Further improvements were made to suppress multipacting effects in the working area.To operate stably with the beam,higher-order mode dampers were applied to better address the coupling bunch instability than in previous designs,along with thermal analysis to achieve the desired RF performance.Comprehensive simulation studies demonstrated the stable operation of the RF cavity at the defined beam parameters in the WALS design.A prototype RF cavity was then developed,and the RF performance results in a low-power test showed good agreement with the design and simulation,exhibiting readiness for high-power experiments and operation.展开更多
There are many traditional villages with well-preserved architectural types and images in the Jingmai Mountain,Yunnan Province.Through field investigations in traditional villages in the research area,this study appli...There are many traditional villages with well-preserved architectural types and images in the Jingmai Mountain,Yunnan Province.Through field investigations in traditional villages in the research area,this study applied the architectural typology,analyzed Nuogang Village of the Dai Nationality and Wengji Village of the Bulang Nationality from 3 perspectives of“point,line and surface”,explored the characteristics of village,architecture and landscape,and extracted the“prototypes”,tried to figure out the problems of the villages and then propose corresponding protection strategies,so as to support the preservation,renovation,improvement and utilization of traditional villages.展开更多
Air quality estimation assesses the pollution level in the air,supports public health warnings,and is a valuable tool in environmental management.Although air sensors have proven helpful in this task,sensors are often...Air quality estimation assesses the pollution level in the air,supports public health warnings,and is a valuable tool in environmental management.Although air sensors have proven helpful in this task,sensors are often expensive and difficult to install,while cameras are becoming more popular and accessible,from which images can be collected as data for deep learning models to solve the above task.This leads to another problem:several labeled images are needed to achieve high accuracy when deep-learningmodels predict air quality.In this research,we have threemain contributions:(1)Collect and publish an air quality estimation dataset,namely PTIT_AQED,including environmental image data and air quality;(2)Propose a deep learning model to predict air quality with few data,called PTIT_FAQE(PTIT Few-shot air quality estimation).We build PTIT_FAQE based on EfficientNet-a CNN architecture that ensures high performance in deep learning applications and Few-shot Learning with Prototypical Networks.This helps the model use only a fewtraining data but still achieve high accuracy in air quality estimation.And(3)conduct experiments to prove the superiority of PTIT_FAQE compared to other studies on both PTIT_AQED and APIN datasets.The results show that our model achieves an accuracy of 0.9278 and an F1-Score of 0.9139 on the PTIT_AQED dataset and an accuracy of 0.9467 and an F1-Score of 0.9371 on the APIN dataset,which demonstrate a significant performance improvement compared to previous studies.We also conduct detailed experiments to evaluate the impact of each component on model performance.展开更多
Since the introduction of vision Transformers into the computer vision field,many vision tasks such as semantic segmentation tasks,have undergone radical changes.Although Transformer enhances the correlation of each l...Since the introduction of vision Transformers into the computer vision field,many vision tasks such as semantic segmentation tasks,have undergone radical changes.Although Transformer enhances the correlation of each local feature of an image object in the hidden space through the attention mechanism,it is difficult for a segmentation head to accomplish the mask prediction for dense embedding of multi-category and multi-local features.We present patch prototype vision Transformer(PPFormer),a Transformer architecture for semantic segmentation based on knowledge-embedded patch prototypes.1)The hierarchical Transformer encoder can generate multi-scale and multi-layered patch features including seamless patch projection to obtain information of multiscale patches,and feature-clustered self-attention to enhance the interplay of multi-layered visual information with implicit position encodes.2)PPFormer utilizes a non-parametric prototype decoder to extract region observations which represent significant parts of the objects by unlearnable patch prototypes and then calculate similarity between patch prototypes and pixel embeddings.The proposed contrasting patch prototype alignment module,which uses new patch prototypes to update prototype bank,effectively maintains class boundaries for prototypes.For different application scenarios,we have launched PPFormer-S,PPFormer-M and PPFormer-L by expanding the scale.Experimental results demonstrate that PPFormer can outperform fully convolutional networks(FCN)-and attention-based semantic segmentation models on the PASCAL VOC 2012,ADE20k,and Cityscapes datasets.展开更多
A team of researchers from the University of Science and Technology of China(USTC)of the Chinese Academy of Sciences(CAS)and its partners have made significant advancements in random quantum circuit sampling with Zuch...A team of researchers from the University of Science and Technology of China(USTC)of the Chinese Academy of Sciences(CAS)and its partners have made significant advancements in random quantum circuit sampling with Zuchongzhi-3,a superconducting quantum computing prototype featuring 105 qubits and 182 couplers.展开更多
To enable simultaneous transmit and receive(STAR)on the same frequency in a densely deployed space with multi-interference sources,this work proposes a digitally-assisted analog selfinterference cancellation method,wh...To enable simultaneous transmit and receive(STAR)on the same frequency in a densely deployed space with multi-interference sources,this work proposes a digitally-assisted analog selfinterference cancellation method,which can acquire reference signals through flexible wired/wireless switching access.Based on this method,the Minimum Mean Square Error algorithm with known channel state information is derived in detail,determining the upper limit of the cancellation performance,and the Adaptive Dithered Linear Search algorithm for real-time engineering cancellation is given.The correctness of theoretical analysis is verified by the practical self-interference channel measured by a vector network analyzer.Furthermore,we have designed and implemented the corresponding multiinterference cancellation prototype with the digitallyassisted structure,capable of handling multiple interferences(up to three)and supporting a large receive bandwidth of 100 MHz as well as a wide frequency coverage from 30 MHz to 3000 MHz.Prototype test results demonstrate that in the presence of three interferences,when the single interference bandwidth is 0.2/2/20 MHz(corresponding to the receive bandwidth of 2/20/100 MHz),the cancellation performance can reach 46/32/22 dB or more.展开更多
Towards optimal k-prototype discovery,k-means-like algorithms give us inspirations of central samples collection,yet the unstable seed samples selection,the hypothesis of a circle-like pattern,and the unknown K are st...Towards optimal k-prototype discovery,k-means-like algorithms give us inspirations of central samples collection,yet the unstable seed samples selection,the hypothesis of a circle-like pattern,and the unknown K are still challenges,particularly for non-predetermined data patterns.We propose an adaptive k-prototype clustering method(kProtoClust)which launches cluster exploration with a sketchy division of K clusters and finds evidence for splitting and merging.On behalf of a group of data samples,support vectors and outliers from the perspective of support vector data description are not the appropriate candidates for prototypes,while inner samples become the first candidates for instability reduction of seeds.Different from the representation of samples in traditional,we extend sample selection by encouraging fictitious samples to emphasize the representativeness of patterns.To get out of the circle-like pattern limitation,we introduce a convex decomposition-based strategy of one-cluster-multiple-prototypes in which convex hulls of varying sizes are prototypes,and accurate connection analysis makes the support of arbitrary cluster shapes possible.Inspired by geometry,the three presented strategies make kProtoClust bypassing the K dependence well with the global and local position relationship analysis for data samples.Experimental results on twelve datasets of irregular cluster shape or high dimension suggest that kProtoClust handles arbitrary cluster shapes with prominent accuracy even without the prior knowledge K.展开更多
The primary challenge in weakly supervised semantic segmentation is effectively leveraging weak annotations while minimizing the performance gap compared to fully supervised methods.End-to-end model designs have gaine...The primary challenge in weakly supervised semantic segmentation is effectively leveraging weak annotations while minimizing the performance gap compared to fully supervised methods.End-to-end model designs have gained significant attention for improving training efficiency.Most current algorithms rely on Convolutional Neural Networks(CNNs)for feature extraction.Although CNNs are proficient at capturing local features,they often struggle with global context,leading to incomplete and false Class Activation Mapping(CAM).To address these limitations,this work proposes a Contextual Prototype-Based End-to-End Weakly Supervised Semantic Segmentation(CPEWS)model,which improves feature extraction by utilizing the Vision Transformer(ViT).By incorporating its intermediate feature layers to preserve semantic information,this work introduces the Intermediate Supervised Module(ISM)to supervise the final layer’s output,reducing boundary ambiguity and mitigating issues related to incomplete activation.Additionally,the Contextual Prototype Module(CPM)generates class-specific prototypes,while the proposed Prototype Discrimination Loss and Superclass Suppression Loss guide the network’s training,(LPDL)(LSSL)effectively addressing false activation without the need for extra supervision.The CPEWS model proposed in this paper achieves state-of-the-art performance in end-to-end weakly supervised semantic segmentation without additional supervision.The validation set and test set Mean Intersection over Union(MIoU)of PASCAL VOC 2012 dataset achieved 69.8%and 72.6%,respectively.Compared with ToCo(pre trained weight ImageNet-1k),MIoU on the test set is 2.1%higher.In addition,MIoU reached 41.4%on the validation set of the MS COCO 2014 dataset.展开更多
文摘Neural Networks (NN) are the functional unit of Deep Learning and are known to mimic the behavior of the human brain to solve complex data-driven problems. Whenever we train our own neural networks, we need to take care of something called the generalization of the neural network. The performance of Artificial Neural Networks (ANN) mostly depends upon its generalization capability. In this paper, we propose an innovative approach to enhance the generalization capability of artificial neural networks (ANN) using structural redundancy. A novel perspective on handling input data prototypes and their impact on the development of generalization, which could improve to ANN architectures accuracy and reliability is described.
基金the National Nature Science Foundation of China(Nos.51805474,51622510,U1609207)Science Fund for Creative Research Groups of National Natural Science Foundation of China (No.51821093)China Postdoctoral Science Foundation (No.2017M621915).
文摘A native organ has heterogeneous structures, sirength, and cell components. It is a big challenge to fabricate organ prototypes with controllable shapes, strength, and cells. Herein, a hybrid method is developed to fabricate organ prototypes with controlled cell deposition by integrating extrusion-based 3D printing, electrospinning, and 3D bioprinting. Multi-scale sheets were first fabricated by 3D printing and electrospinning;then, all the sheets were assembled into organ prototypes by sol-gel react io n duri ng bioprinting. With this method, macroscale structures fabricated by 3D printing ensure the customized structures and provide mechanical support, nanoscale structures fabricated by electrospinning offer a favorable environment for cell growth, and different types of cells with controllable densities are deposited in accurate locations by bioprinting. The results show that L929 mouse fibroblasts encapsulated in the structures exhibited over 90% survival within 10 days and maintai ned a high proliferation rate. Furthermore, the cells grew in spherical shapes first and then migrated to the nano scale fibers showing stretched morphology. Additionally, a branched vascular structure was successfully fabricated using the presented method. Compared with other methods, this strategy offers an easy way to simultancously realize the shape control, nanolibrous structures, and cell accurate deposition, which will have potemidi applications in tissue cngineering.
文摘The effect of time and environment on the dimension precision and mass of LOM prototypes was experimentally investigated.It is to identify the stability of the dimension of LOM prototypes after forming.The results show that the dimension and the mass tendency to grow,which is mainly caused by elastic recovery and moisture absorption and is characterized principally by the growth of Z dimension.Self restraint can be a significant factor to influence Z growth of LOM prototypes.
文摘The prototype theory suggests that many metal concepts we have are really prototypes.It claims that children first learn words that are "basic" because they reflect aspects of the world,prototypes, which stand out automatically from the rest of what they see.Basic level words should be taught first.
文摘An in-depth study of bra pattern designs based on the existing bodice blocks was conducted to improve bra fit.The two popular bra prototypes,D's and Y's prototypes developed based on the existing bodice blocks for adult women,were first analyzed to understand their structural differences.Four bra samples were created and modified with respect to the standard shape and size of 75 B female mannequin breasts to compare the fit of the two bra prototypes.The fitness of these four bra samples was then tested on the mannequin and also on a real model of the same size.The examples demonstrated in the paper illustrate the principles and procedures for designing good-fit bras,and the bodice blocks using to develop bra prototypes in this study can also be replaced and widespread applied in other kind of bodice blocks in the future.
文摘In order to reveal the appearance of the clothing prototype on the human body,the characteristics of the human body’s structure above the waist section were studied.Based on the experimental data of the fit prototype,three-dimensional prototypes features were comparatively analyzed.And then objectively evaluating the relationship was conducted between the planar structure lines of different prototypes and the human body.The results showed that the prototypes analyzed basically conformed to the size of the human body.However,when they were worn on the human body,there were problems in the structure and forming.The main reason was that the side seam was skewed to different degrees.The results of this study provide reference for many practitioners to choose prototypes.
文摘Cognitive linguistics is a new approach to language study, which can offer better explanation for language phenomena, and provide more theoretical instructions for English learning. In recent years, the prototype theory, as the cornerstone of cognitive linguistics, has been employed in different research fields, such as phonology, syntax, semantics, English teaching, etc..This thesis attempts to review and discuss the researches done so far on semantics and categorization based on a cognitive theory -- the prototype theory.
文摘In this paper we report the results of combined cycle- and life-aging and abuse tests carried out under severe conditions on Li<sub>4</sub>Ti<sub>5</sub>O<sub>12</sub>/LiFePO<sub>4</sub> lithium-ion stacked prototypes using a PYR<sub>14</sub> FSI-LiTFSI ionic liquid electrolyte. No relevant degradation phenomena took place within ionic liquid electrolyte during prolonged inactivity period or overcharging. No fire/explosion or venting event as well as no gas development occurred during abuse tests, which led only to modest raise in temperature. Therefore, electrodes based on Li<sub>4</sub>Ti<sub>5</sub>O<sub>12</sub> and LiFePO<sub>4</sub> active materials can be favorably combined with non-volatile and non-flammable pyrrolidinium FSI ionic liquid electrolytes to realize highly safe lithium-ion battery systems.
文摘Research on reconstructing imperfect faces is a challenging task.In this study,we explore a data-driven approach using a pre-trained MICA(MetrIC fAce)model combined with 3D printing to address this challenge.We propose a training strategy that utilizes the pre-trained MICA model and self-supervised learning techniques to improve accuracy and reduce the time needed for 3D facial structure reconstruction.Our results demonstrate high accuracy,evaluated by the geometric loss function and various statistical measures.To showcase the effectiveness of the approach,we used 3D printing to create a model that covers facial wounds.The findings indicate that our method produces a model that fits well and achieves comprehensive 3D facial reconstruction.This technique has the potential to aid doctors in treating patients with facial injuries.
文摘The 1.6GeV synchrotron of China Spallation Neutron Source(CSNS)project is a Rapid Cycling Synchrotron (RCS),which accelerates a high-intensity proton beam from 80MeV to 1.6GeV at a repetition rate of 25Hz.The RCS magnet system consists of 24 dipole magnets(main dipoles),48 quadrupole magnets(main quadrupoles),16 sextupole magnets,some tune shift quadrupoles and corrector magnets.All the magnets are of large aperture for a high beam power of 0.1MW,one design issue is the fringe field at pole end.And the main dipoles and main quadrupoles work at 25Hz repetition rate,the eddy current is an additional issue.In this paper the magnet design of the two kinds of main magnets will be described.
文摘无监督异常检测因只需要正常样本进行训练而被广泛应用于工业质检等领域。直接将现有的单类别异常检测方法应用到多类别异常检测中会导致性能显著下降,其中基于知识蒸馏的异常检测方法将预训练的教师模型关于正常样本的特征知识蒸馏到学生模型中,然而它们在多类别异常检测中存在无法保证学生模型只学习到正常样本知识的问题。文中提出一种基于反向知识蒸馏框架的无监督多类别异常检测方法(Prototype based Reverse Distillation,PRD),其通过Multi-class Normal Prototype模块和Sparse Prototype Recall训练策略来学习教师模型关于多类别正常样本特征的Prototype,并以此来过滤学生模型的输入特征,从而确保学生模型只学习到教师模型关于正常样本的特征知识。PRD在多种工业异常检测数据集上性能均超越了现有的SOTA方法,定性、定量和消融实验验证了PRD整体框架和内部模块的有效性。
基金supported by National Natural Science Foundation of China(Nos.12222513,12105345,12175292,and No.12405178)。
文摘Radio frequency(RF)cavities for advanced storage rings,also known as diffraction-limited storage rings,are under development.To this end,a competitive and promising approach involves normal-conducting continuous wave technology.The design and preliminary test of a 499.654 MHz RF cavity for the Wuhan Advanced Light Source(WALS)based on specific beam parameters were conducted at the SSRF.Multi-objective evolutionary algorithms have been utilized to optimize RF properties,such as the power loss and power density,resulting in better performance in the continuous wave mode.Further improvements were made to suppress multipacting effects in the working area.To operate stably with the beam,higher-order mode dampers were applied to better address the coupling bunch instability than in previous designs,along with thermal analysis to achieve the desired RF performance.Comprehensive simulation studies demonstrated the stable operation of the RF cavity at the defined beam parameters in the WALS design.A prototype RF cavity was then developed,and the RF performance results in a low-power test showed good agreement with the design and simulation,exhibiting readiness for high-power experiments and operation.
文摘There are many traditional villages with well-preserved architectural types and images in the Jingmai Mountain,Yunnan Province.Through field investigations in traditional villages in the research area,this study applied the architectural typology,analyzed Nuogang Village of the Dai Nationality and Wengji Village of the Bulang Nationality from 3 perspectives of“point,line and surface”,explored the characteristics of village,architecture and landscape,and extracted the“prototypes”,tried to figure out the problems of the villages and then propose corresponding protection strategies,so as to support the preservation,renovation,improvement and utilization of traditional villages.
文摘Air quality estimation assesses the pollution level in the air,supports public health warnings,and is a valuable tool in environmental management.Although air sensors have proven helpful in this task,sensors are often expensive and difficult to install,while cameras are becoming more popular and accessible,from which images can be collected as data for deep learning models to solve the above task.This leads to another problem:several labeled images are needed to achieve high accuracy when deep-learningmodels predict air quality.In this research,we have threemain contributions:(1)Collect and publish an air quality estimation dataset,namely PTIT_AQED,including environmental image data and air quality;(2)Propose a deep learning model to predict air quality with few data,called PTIT_FAQE(PTIT Few-shot air quality estimation).We build PTIT_FAQE based on EfficientNet-a CNN architecture that ensures high performance in deep learning applications and Few-shot Learning with Prototypical Networks.This helps the model use only a fewtraining data but still achieve high accuracy in air quality estimation.And(3)conduct experiments to prove the superiority of PTIT_FAQE compared to other studies on both PTIT_AQED and APIN datasets.The results show that our model achieves an accuracy of 0.9278 and an F1-Score of 0.9139 on the PTIT_AQED dataset and an accuracy of 0.9467 and an F1-Score of 0.9371 on the APIN dataset,which demonstrate a significant performance improvement compared to previous studies.We also conduct detailed experiments to evaluate the impact of each component on model performance.
基金supported in part by the Gansu Haizhi Characteristic Demonstration Project(No.GSHZTS2022-2).
文摘Since the introduction of vision Transformers into the computer vision field,many vision tasks such as semantic segmentation tasks,have undergone radical changes.Although Transformer enhances the correlation of each local feature of an image object in the hidden space through the attention mechanism,it is difficult for a segmentation head to accomplish the mask prediction for dense embedding of multi-category and multi-local features.We present patch prototype vision Transformer(PPFormer),a Transformer architecture for semantic segmentation based on knowledge-embedded patch prototypes.1)The hierarchical Transformer encoder can generate multi-scale and multi-layered patch features including seamless patch projection to obtain information of multiscale patches,and feature-clustered self-attention to enhance the interplay of multi-layered visual information with implicit position encodes.2)PPFormer utilizes a non-parametric prototype decoder to extract region observations which represent significant parts of the objects by unlearnable patch prototypes and then calculate similarity between patch prototypes and pixel embeddings.The proposed contrasting patch prototype alignment module,which uses new patch prototypes to update prototype bank,effectively maintains class boundaries for prototypes.For different application scenarios,we have launched PPFormer-S,PPFormer-M and PPFormer-L by expanding the scale.Experimental results demonstrate that PPFormer can outperform fully convolutional networks(FCN)-and attention-based semantic segmentation models on the PASCAL VOC 2012,ADE20k,and Cityscapes datasets.
文摘A team of researchers from the University of Science and Technology of China(USTC)of the Chinese Academy of Sciences(CAS)and its partners have made significant advancements in random quantum circuit sampling with Zuchongzhi-3,a superconducting quantum computing prototype featuring 105 qubits and 182 couplers.
基金supported in part by the National Natural Science Foundation of China under Grant 62071094in part by the National Key Laboratory of Wireless Communications Foundation under Grant IFN202402in part by the Postdoctoral Fellowship Program(Grade C)of China Postdoctoral Science Foundation under Grant GZC20240217.
文摘To enable simultaneous transmit and receive(STAR)on the same frequency in a densely deployed space with multi-interference sources,this work proposes a digitally-assisted analog selfinterference cancellation method,which can acquire reference signals through flexible wired/wireless switching access.Based on this method,the Minimum Mean Square Error algorithm with known channel state information is derived in detail,determining the upper limit of the cancellation performance,and the Adaptive Dithered Linear Search algorithm for real-time engineering cancellation is given.The correctness of theoretical analysis is verified by the practical self-interference channel measured by a vector network analyzer.Furthermore,we have designed and implemented the corresponding multiinterference cancellation prototype with the digitallyassisted structure,capable of handling multiple interferences(up to three)and supporting a large receive bandwidth of 100 MHz as well as a wide frequency coverage from 30 MHz to 3000 MHz.Prototype test results demonstrate that in the presence of three interferences,when the single interference bandwidth is 0.2/2/20 MHz(corresponding to the receive bandwidth of 2/20/100 MHz),the cancellation performance can reach 46/32/22 dB or more.
基金supported by the National Natural Science Foundation of China under Grant No.62162009the Key Technologies R&D Program of He’nan Province under Grant No.242102211065+1 种基金the Scientific Research Innovation Team of Xuchang University under GrantNo.2022CXTD003Postgraduate Education Reform and Quality Improvement Project of Henan Province under Grant No.YJS2024JD38.
文摘Towards optimal k-prototype discovery,k-means-like algorithms give us inspirations of central samples collection,yet the unstable seed samples selection,the hypothesis of a circle-like pattern,and the unknown K are still challenges,particularly for non-predetermined data patterns.We propose an adaptive k-prototype clustering method(kProtoClust)which launches cluster exploration with a sketchy division of K clusters and finds evidence for splitting and merging.On behalf of a group of data samples,support vectors and outliers from the perspective of support vector data description are not the appropriate candidates for prototypes,while inner samples become the first candidates for instability reduction of seeds.Different from the representation of samples in traditional,we extend sample selection by encouraging fictitious samples to emphasize the representativeness of patterns.To get out of the circle-like pattern limitation,we introduce a convex decomposition-based strategy of one-cluster-multiple-prototypes in which convex hulls of varying sizes are prototypes,and accurate connection analysis makes the support of arbitrary cluster shapes possible.Inspired by geometry,the three presented strategies make kProtoClust bypassing the K dependence well with the global and local position relationship analysis for data samples.Experimental results on twelve datasets of irregular cluster shape or high dimension suggest that kProtoClust handles arbitrary cluster shapes with prominent accuracy even without the prior knowledge K.
基金funding from the following sources:National Natural Science Foundation of China(U1904119)Research Programs of Henan Science and Technology Department(232102210054)+3 种基金Chongqing Natural Science Foundation(CSTB2023NSCQ-MSX0070)Henan Province Key Research and Development Project(231111212000)Aviation Science Foundation(20230001055002)supported by Henan Center for Outstanding Overseas Scientists(GZS2022011).
文摘The primary challenge in weakly supervised semantic segmentation is effectively leveraging weak annotations while minimizing the performance gap compared to fully supervised methods.End-to-end model designs have gained significant attention for improving training efficiency.Most current algorithms rely on Convolutional Neural Networks(CNNs)for feature extraction.Although CNNs are proficient at capturing local features,they often struggle with global context,leading to incomplete and false Class Activation Mapping(CAM).To address these limitations,this work proposes a Contextual Prototype-Based End-to-End Weakly Supervised Semantic Segmentation(CPEWS)model,which improves feature extraction by utilizing the Vision Transformer(ViT).By incorporating its intermediate feature layers to preserve semantic information,this work introduces the Intermediate Supervised Module(ISM)to supervise the final layer’s output,reducing boundary ambiguity and mitigating issues related to incomplete activation.Additionally,the Contextual Prototype Module(CPM)generates class-specific prototypes,while the proposed Prototype Discrimination Loss and Superclass Suppression Loss guide the network’s training,(LPDL)(LSSL)effectively addressing false activation without the need for extra supervision.The CPEWS model proposed in this paper achieves state-of-the-art performance in end-to-end weakly supervised semantic segmentation without additional supervision.The validation set and test set Mean Intersection over Union(MIoU)of PASCAL VOC 2012 dataset achieved 69.8%and 72.6%,respectively.Compared with ToCo(pre trained weight ImageNet-1k),MIoU on the test set is 2.1%higher.In addition,MIoU reached 41.4%on the validation set of the MS COCO 2014 dataset.
