|
|
|
题名
|
作者
|
年代
|
出处
|
被引量
|
| 1 | DRIB:Interpreting DNN with Dynamic Reasoning and Information Bottleneck显示文摘The interpretability of deep neural networks has aroused widespread concern in the academic and industrial fields.This paper proposes a new method named the dynamic reasoning and information bottleneck(DRIB)to improve human interpretability and understandability.In the method,a novel dynamic reasoning decision algorithmwas proposed to reduce multiply accumulate operations and improve the interpretability of the calculation.The information bottleneck was introduced to the DRIB model to verify the attribution correctness of the dynamic reasoning module.The DRIB reduces the burden approximately 50%by decreasing the amount of computation.In addition,DRIB keeps the correct rate at approximately 93%.The information bottleneck theory verifies the effectiveness of this method,and the credibility is approximately 85%.In addition,through visual verification of this method,the highlighted area can reach 50%of the predicted area,which can be explained more obviously.Some experiments prove that the dynamic reasoning decision algorithm and information bottleneck theory can be combined with each other.Otherwise,the method provides users with good interpretability and understandability,making deep neural networks trustworthy. | Yu Si Keyang Cheng Zhou Jiang Hao Zhou Rabia Tahir | 2022 | 国际计算机前沿大会会议论文集2022，，1： | 0 |
| 2 | An Edge Computing Algorithm Based on Multi-Level Star Sensor Cloud显示文摘Star sensors are an important means of autonomous navigation and access to space information for satellites.They have been widely deployed in the aerospace field.To satisfy the requirements for high resolution,timeliness,and confidentiality of star images,we propose an edge computing algorithm based on the star sensor cloud.Multiple sensors cooperate with each other to forma sensor cloud,which in turn extends the performance of a single sensor.The research on the data obtained by the star sensor has very important research and application values.First,a star point extraction model is proposed based on the fuzzy set model by analyzing the star image composition,which can reduce the amount of data computation.Then,a mappingmodel between content and space is constructed to achieve low-rank image representation and efficient computation.Finally,the data collected by the wireless sensor is delivered to the edge server,and a differentmethod is used to achieve privacy protection.Only a small amount of core data is stored in edge servers and local servers,and other data is transmitted to the cloud.Experiments show that the proposed algorithm can effectively reduce the cost of communication and storage,and has strong privacy. | Siyu Ren Shi Qiu Keyang Cheng | 2023 | Computer Modeling in Engineering & Sciences2023，，8： | 0 |
| 3 | Video Stabilization via Prediction with Time-Series Network and Image Inpainting with Pyramid Fusion显示文摘Due to the poor filling effect of the video image defect commonly used in the video stabilization field, the video is seemed still unstable after the image stabilization process, which seriously affects the visual effect. To solve this problem, we improve a video stabilization method based on time-series network prediction and pyramid fusion restoration is proposed to optimize the visual effect after image stabilization.The flow of the proposed method is as follows: First,it is adaptive to determine whether the defect of the corresponding frame at the current time needs padding inpainting. Then, for the frame that needs to be inpainting,the frames generated before the current moment are sent to the model combining the convolutional neural networks and the gate recurrent unit to predict the part to be filled. Next the current defect image and the complete image to be filled are brought into the Laplacian pyramid reconstruction, and the improved weighted optimal suture is introduced for splicing during the fusion. Finally, the video frame is cut after reconstruction. The method is tested on a data set composed of videos commonly used in the field of video stabilization. The experimental results show that the average peak signal to noise ratio of the method is 2 to 5 d B higher than that of the comparison algorithm, and the average structural similarity index is improved by about 2% to 7% compared with the contrast algorithm. | CHENG Keyang LI Shichao RONG Lan WANG Wenshan SHI Wenxi ZHAN Yongzhao | 2021 | Chinese Journal of Electronics2021，30，6： | 0 |
| 4 | Multi-Directional Reconstruction Algorithm for Panoramic Camera显示文摘A panorama can reflect the surrounding scenery because it is an image with a wide angle of view.It can be applied in virtual reality,smart homes and other fields as well.A multi-directional reconstruction algorithm for panoramic camera is proposed in this paper according to the imaging principle of dome camera,as the distortion inevitably exists in the captured panorama.First,parameters of a panoramic image are calculated.Then,a weighting operator with location information is introduced to solve the problem of rough edges by taking full advantage of pixels.Six directions of the mapping model are built,which include up,down,left,right,front and back,according to the correspondence between cylinder and spherical coordinates.Finally,multi-directional image reconstruction can be realized.Various experiments are performed in panoramas(1024×1024)with 30 different shooting scenes.Results show that the azimuth image can be reconstructed quickly and accurately.The fuzzy edge can be alleviated effectively.The rate of pixel utilization can reach 84%,and it is 33%higher than the direct mapping algorithm.Large scale distortion is also further studied. | Shi Qiu Bin Li Keyang Cheng Xiao Zhang Guifang Duan Feng Li | 2020 | Computers, Materials & Continua2020，，10： | 0 |
您所在的机构暂未开通此部分的功能，请联系管理员