检索结果-内蒙古大学图书馆

Fast Algorithm for Parallel Solving Inversion of Large Scale Small Matrices Based on Gpu

学校读者我要写书评

暂无评论

SSRN

SSRN 2022年

作者： Jin, Xuebin Chen, Yewang Fan, Wentao Zhang, Yong Du, Jixiang The College of Computer Science and Technology Huaqiao University Xiamen China Fujian Key Laboratory of Big Data Intelligence and Security Huaqiao University Xiamen China Xiamen Key Laboratory of Computer Vision and Pattern Recognition Huaqiao University China Provincial Key Laboratory for Computer Information Processing Technology Soochow University Soochow China College of Mechanical Engineering and Automation Huaqiao University Xiamen China

Inverting a matrix is time-consuming, and many works focus on accelerating inverting a single large matrix by GPU. However, the problem of inverting large-scale small matrices has little attention. In this paper, we propose a Revised In-Place Inversion algorithm for inverting large-scale small matrices, which runs on the CUDA platform and utilizes multicore GPUs. The proposed algorithm is well-suited for large-scale-small matrices (dimension $n \leq 32$), which can invert millions of small matrices within tens of milliseconds. In addition, we find there is an upper bound of input data size for each GPU device, the performance will degrade if the input data size is too large. Hence, we improve the proposed method by dividing matrices into batches according to this finding. Experimental results show that this strategy can effectively alleviate the performance degradation for inverting large scale small matrices, and maintain the high-performance execution of the algorithm. © 2022, The Authors. All rights reserved.

关键词： Matrix algebra

Attention-Guided Multi-scale Interaction Network for Face Super-Resolution

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wan, Xujie Li, Wenjie Gao, Guangwei Lu, Huimin Yang, Jian Lin, Chia-Wen The Institute of Advanced Technology Nanjing University of Posts and Telecommunications Nanjing210046 China Key Laboratory of Artificial Intelligence Ministry of Education Shanghai200240 China The Provincial Key Laboratory for Computer Information Processing Technology Soochow University Suzhou215006 China The Pattern Recognition and Intelligent System Laboratory School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing100080 China The School of Automation Southeast University Nanjing210096 China The School of Computer Science and Technology Nanjing University of Science and Technology Nanjing210094 China The Department of Electrical Engineering National Tsing Hua University Hsinchu30013 Taiwan

Recently, CNN and Transformer hybrid networks demonstrated excellent performance in face super-resolution (FSR) tasks. Since numerous features at different scales in hybrid networks, how to fuse these multi-scale features and promote their complementarity is crucial for enhancing FSR. However, existing hybrid network-based FSR methods ignore this, only simply combining the Transformer and CNN. To address this issue, we propose an attention-guided Multi-scale interaction network (AMINet), which contains local and global feature interactions as well as encoder-decoder phases feature interactions. Specifically, we propose a Local and Global Feature Interaction Module (LGFI) to promote fusions of global features and different receptive fields' local features extracted by our Residual Depth Feature Extraction Module (RDFE). Additionally, we propose a Selective Kernel Attention Fusion Module (SKAF) to adaptively select fusions of different features within LGFI and encoder-decoder phases. Our above design allows the free flow of multi-scale features from within modules and between encoder and decoder, which can promote the complementarity of different scale features to enhance FSR. Comprehensive experiments confirm that our method consistently performs well with less computational consumption and faster inference. Copyright © 2024, The Authors. All rights reserved.

关键词： Decoding

FDFlowNet: Fast optical flow estimation using a deep lightweight network

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Kong, Lingtong Yang, Jie Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University China Institute of Medical Robotics Shanghai Jiao Tong University China

Significant progress has been made for estimating optical flow using deep neural networks. Advanced deep models achieve accurate flow estimation often with a considerable computation complexity and time-consuming training processes. In this work, we present a lightweight yet effective model for real-time optical flow estimation, termed FDFlowNet (fast deep flownet). We achieve better or similar accuracy on the challenging KITTI and Sintel benchmarks while being about 2 times faster than PWC-Net. This is achieved by a carefully-designed structure and newly proposed components. We first introduce an U-shape network for constructing multi-scale feature which benefits upper levels with global receptive field compared with pyramid network. In each scale, a partial fully connected structure with dilated convolution is proposed for flow estimation that obtains a good balance among speed, accuracy and number of parameters compared with sequential connected and dense connected structures. Experiments demonstrate that our model achieves state-of-the-art performance while being fast and lightweight. Copyright © 2020, The Authors. All rights reserved.

关键词： Optical flows

Bioimage-based protein subcellular location prediction： a comprehensive review

学校读者我要写书评

暂无评论

Frontiers of Computer Science 2018年第1期12卷 26-39页

作者： Ying-Ying XU Li-Xiu YAO Hong-Bin SHEN Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai 200240 China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai 200240 China

Subcellular localization of proteins can provide key hints to infer their functions and structures in cells. With the breakthrough of recent molecule imaging techniques, the usage of 2D bioimages has become increasingly popular in automatically analyzing the protein subcellular location pat- terns. Compared with the widely used protein 1D amino acid sequence data, the images of protein distribution are more intuitive and interpretable, making the images a better choice at many applications for revealing the dynamic char- acteristics of proteins, such as detecting protein translocation and quantification of proteins. In this paper, we systemati- cally reviewed the recent progresses in the field of automated image-based protein subcellular location prediction, and clas- sified them into four categories including growing of bioim- age databases, description of subcellular location distribution patterns, classification methods, and applications of the pre- diction systems. Besides, we also discussed some potential directions in this field.

关键词： bioimage informatics protein subcellular loca-tion prediction global and local features multi-location pro-tein recognition

Learning bronchiole-sensitive airway segmentation cnns by feature recalibration and attention distillation 23rd

学校读者我要写书评

暂无评论

Learning bronchiole-sensitive airway segmentation cnns by fe...

23rd International Conference on Medical image Computing and Computer-Assisted Intervention, MICCAI 2020

作者： Qin, Yulei Zheng, Hao Gu, Yun Huang, Xiaolin Yang, Jie Wang, Lihui Zhu, Yue-Min Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai China Institute of Medical Robotics Shanghai Jiao Tong University Shanghai China Key Laboratory of Intelligent Medical Image Analysis and Precise Diagnosis of Guizhou Province College of Computer Science and Technology Guizhou University Guiyang China UdL INSA Lyon CREATIS CNRS UMR 5220 INSERM U1206 Lyon France

ISBN: (纸本)9783030597092

Training deep convolutional neural networks (CNNs) for airway segmentation is challenging due to the sparse supervisory signals caused by severe class imbalance between long, thin airways and background. In view of the intricate pattern of tree-like airways, the segmentation model should pay extra attention to the morphology and distribution characteristics of airways. We propose a CNNs-based airway segmentation method that enjoys superior sensitivity to tenuous peripheral bronchioles. We first present a feature recalibration module to make the best use of learned features. Spatial information of features is properly integrated to retain relative priority of activated regions, which benefits the subsequent channel-wise recalibration. Then, attention distillation module is introduced to reinforce the airway-specific representation learning. High-resolution attention maps with fine airway details are passing down from late layers to previous layers iteratively to enrich context knowledge. Extensive experiments demonstrate considerable performance gain brought by the two proposed modules. Compared with state-of-the-art methods, our method extracted much more branches while maintaining competitive overall segmentation performance. © Springer Nature Switzerland AG 2020.

关键词： Distillation

DreamNet: A Deep Riemannian Network based on SPD Manifold Learning for Visual Classification

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Wang, Rui Wu, Xiao-Jun Chen, Ziheng Xu, Tianyang Kittler, Josef School of Artificial Intelligence and Computer Science Jiangnan University Wuxi214122 China Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence Jiangnan University China Centre for Vision Speech and Signal Processing University of Surrey GuildfordGU2 7XH United Kingdom School of Artificial Intelligence and Computer Science Jiangnan University China

image set-based visual classification methods have achieved remarkable performance, via characterising the image set in terms of a non-singular covariance matrix on a symmetric positive definite (SPD) manifold. To adapt to complicated visual scenarios better, several Riemannian networks (RiemNets) for SPD matrix nonlinear processing have recently been studied. However, it is pertinent to ask, whether greater accuracy gains can be achieved by simply increasing the depth of RiemNets. The answer appears to be negative, as deeper RiemNets tend to lose generalization ability. To explore a possible solution to this issue, we propose a new architecture for SPD matrix learning. Specifically, to enrich the deep representations, we adopt SPDNet [1] as the backbone, with a stacked Riemannian autoencoder (SRAE) built on the tail. The associated reconstruction error term can make the embedding functions of both SRAE and of each RAE an approximate identity mapping, which helps to prevent the degradation of statistical information. We then insert several residual-like blocks with shortcut connections to augment the representational capacity of SRAE, and to simplify the training of a deeper network. The experimental evidence demonstrates that our DreamNet can achieve improved accuracy with increased depth of the network. Copyright © 2022, The Authors. All rights reserved.

关键词： Covariance matrix

Progressive low/high-resolution Space Attention Fusion Network for Single image Super-Resolution

学校读者我要写书评

暂无评论

Journal of Physics: Conference Series 2021年第1期1828卷

作者： Chengzu Zhong Yue Zhou Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai China

The general single image super-resolution methods mainly extract features from the high-resolution (HR) space by the pre-upscaling step at the beginning of the network or from the low-resolution (LR) space before the post-upscaling step at the end of the network. The former way requires high computation as well as misleading the network by wrong artificial priors. The latter way cannot learn mapping well by only conducting simple operations in HR space. In this paper, we aim to utilize the features from LR and HR space more efficiently and propose the novel network, which applies a frequency-slicing mechanism to divide features into LR and HR space, a direction-aware fusion residual group to extract distinctive features in LR space and an attention fusion module to recalibrate features in HR space. The experimental results demonstrate that our model is superior to the state-of-the-art methods upon quantitative metrics and visual quality.

关键词：

Edge-Aware Graph Attention Network for Ratio of Edge-User Estimation in Mobile Networks

学校读者我要写书评

暂无评论

Edge-Aware Graph Attention Network for Ratio of Edge-User Es...

International Conference on pattern recognition

作者： Jiehui Deng Sheng Wan Xiang Wang Enmei Tu Xiaolin Huang Jie Yang Chen Gong PCA Lab the Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai China Hong Kong Polytechnic University Hong Kong SAR China

Estimating the Ratio of Edge-Users (REU) is an important issue in mobile networks, as it helps the subsequent adjustment of loads in different cells. However, existing approaches usually determine the REU manually, which are experience-dependent and labor-intensive, and thus the estimated REU might be imprecise. Considering the inherited graph structure of mobile networks, in this paper, we utilize a graph-based deep learning method for automatic REU estimation, where the practical cells are deemed as nodes and the load switchings among them constitute edges. Concretely, Graph Attention Network (GAT) is employed as the backbone of our method due to its impressive generalizability in dealing with networked data. Nevertheless, conventional GAT cannot make full use of the information in mobile networks, since it only incorporates node features to infer the pairwise importance and conduct graph convolutions, while the edge features that are actually critical in our problem are disregarded. To accommodate this issue, we propose an Edge-Aware Graph Attention Network (EAGAT), which is able to fuse the node features and edge features for REU estimation. Extensive experimental results on two real-world mobile network datasets demonstrate the superiority of our EAGAT approach to several state-of-the-art methods.

关键词： Deep learning Fuses Estimation Switches pattern recognition

Multi-patch feature pyramid network for weakly supervised object detection in optical remote sensing images

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Shamsolmoali, Pourya Chanussot, Jocelyn Zareapoor, Masoumeh Zhou, Huiyu Yang, Jie The Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai China LJK CNRS Inria Grenoble INP Université Grenoble Alpes Grenoble38000 France The School of Informatics University of Leicester LeicesterLE1 7RH United Kingdom

To read the paper please go to IEEE Transactions on Geoscience and Remote Sensing on IEEE Xplore. Object detection is a challenging task in remote sensing because objects only occupy a few pixels in the images, and the models are required to simultaneously learn object locations and detection. Even though the established approaches well perform for the objects of regular sizes, they achieve weak performance when analyzing small ones or getting stuck in the local minima (e.g. false object parts). Two possible issues stand in their way. First, the existing methods struggle to perform stably on the detection of small objects because of the complicated background. Second, most of the standard methods used hand-crafted features, and do not work well on the detection of objects parts of which are missing. We here address the above issues and propose a new architecture with a multiple patch feature pyramid network (MPFP-Net). Different from the current models that during training only pursue the most discriminative patches, in MPFP-Net the patches are divided into class-affiliated subsets, in which the patches are related and based on the primary loss function, a sequence of smooth loss functions are determined for the subsets to improve the model for collecting small object parts. To enhance the feature representation for patch selection, we introduce an effective method to regularize the residual values and make the fusion transition layers strictly norm-preserving. The network contains bottom-up and crosswise connections to fuse the features of different scales to achieve better accuracy, compared to several state-of-the-art object detection models. Also, the developed architecture is more efficient than the baselines. © 2021, CC BY-NC-SA.

关键词： Object recognition