检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Li, Xiaoxu Chang, Dongliang Ma, Zhanyu Tan, Zheng-Hua Xue, Jing-Hao Cao, Jie Yu, Jingyi Guo, Jun School of Computer and Communication Lanzhou University of Technology China Pattern Recognition and Intelligent System Laboratory School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing China Department of Electronic Systems Aalborg University Denmark Department of Statistical Science University College London United Kingdom School of Information Science and Technology ShanghaiTech University China

A deep neural network of multiple nonlinear layers forms a large function space, which can easily lead to overfitting when it encounters small-sample data. To mitigate overfitting in small-sample classification, learning more discriminative features from small-sample data is becoming a new trend. To this end, this paper aims to find a subspace of neural networks that can facilitate a large decision margin. Specifically, we propose the Orthogonal Softmax Layer (OSL), which makes the weight vectors in the classification layer remain orthogonal during both the training and test processes. The Rademacher complexity of a network using the OSL is only K1, where K is the number of classes, of that of a network using the fully connected classification layer, leading to a tighter generalization error bound. Experimental results demonstrate that the proposed OSL has better performance than the methods used for comparison on four small-sample benchmark datasets, as well as its applicability to large-sample datasets. Codes are available at: https://***/dongliangchang/OSLNet. Copyright © 2020, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Competing Ratio Loss for Multi-class image Classification

Competing Ratio Loss for Multi-class image Classification

引用

IEEE Visual Communications and Image Processing Conference

作者： Ke Zhang Xinsheng Wang Yurong Guo Zhenbing Zhao Zhanyu Ma Department of Electronic and Communication Engineering North China Electric Power University Hebei China Pattern Recognition and Intelligent System Laboratory Beijing University of Posts and Telecommunications Beijing China

Cross-entropy loss function (CEL) is widely used for training a multi-class classification deep convolutional neural network (DCNN). While CEL has been successfully implemented in image classification tasks, it only focuses on the posterior probability of correct class when the labels of training images are one-hot. It cannot be discriminated against the classes not belong to correct class (wrong classes) directly. Negative Log Likelihood Ratio Loss (NLLR) is proposed to better discriminate the correct class from competing wrong classes. But optimization of the loss function is normally presented as a minimization problem. In training DCNN, the value of NLLR is not constantly positive or negative, which affects the convergence of NLLR adversely. So, we propose competing ratio loss (CRL), which calculates the posterior probability ratio between the correct class and competing wrong classes to better widen the difference between the probability of the correct class and the probabilities of wrong classes, which also assures the value of CRL is constantly positive. Through massive experiments, we demonstrate the effectiveness and robustness of CRL on deep convolutional neural networks, our CRL outperforms CEL and NLLR on CIFAR-10/100 datasets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cross-receptive Focused Inference Network for Lightweight Image Super-Resolution

arXiv

引用

arXiv 2022年

作者： Li, Wenjie Li, Juncheng Gao, Guangwei Deng, Weihong Zhou, Jiantao Yang, Jian Qi, Guo-Jun The Intelligent Visual Information Perception Laboratory Institute of Advanced Technology Nanjing University of Posts and Telecommunications Nanjing210046 China The Provincial Key Laboratory for Computer Information Processing Technology Soochow University Suzhou215006 China The School of Communication and Information Engineering Shanghai University Shanghai200444 China Jiangsu Key Laboratory of Image and Video Understanding for Social Safety Nanjing University of Science and Technology Nanjing210094 China The Pattern Recognition and Intelligent System Laboratory School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing100876 China The State Key Laboratory of Internet of Things for Smart City Department of Computer and Information Science Faculty of Science and Technology University of Macau 999078 China The School of Computer Science and Technology Nanjing University of Science and Technology Nanjing210094 China The Research Center for Industries of the Future The School of Engineering Westlake University Hangzhou310024 China OPPO Research SeattleWA98101 United States

Recently, Transformer-based methods have shown impressive performance in single image super-resolution (SISR) tasks due to the ability of global feature extraction. However, the capabilities of Transformers that need to incorporate contextual information to extract features dynamically are neglected. To address this issue, we propose a lightweight Cross-receptive Focused Inference Network (CFIN) that consists of a cascade of CT Blocks mixed with CNN and Transformer. Specifically, in the CT block, we first propose a CNN-based Cross-Scale Information Aggregation Module (CIAM) to enable the model to better focus on potentially helpful information to improve the efficiency of the Transformer phase. Then, we design a novel Cross-receptive Field Guided Transformer (CFGT) to enable the selection of contextual information required for reconstruction by using a modulated convolutional kernel that understands the current semantic information and exploits the information interaction within different self-attention. Extensive experiments have shown that our proposed CFIN can effectively reconstruct images using contextual information, and it can strike a good balance between computational cost and model performance as an efficient model. Source codes will be available at https://***/IVIPLab/CFIN. Copyright © 2022, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Research on Low Altitude Aerial Image Stitching

Research on Low Altitude Aerial Image Stitching

引用

第37届中国控制会议

作者： Jiakun Lu Yongqiang Bai Beijing Institute of Technology Pattern Recognition and Intelligent System

In this paper, we study the problem of low altitude aerial image stitching. Though the traditional approach is well studied, batch-process image stitching is more difficult. In this work, we present a simple and effective approach to handle problems in low altitude aerial image stitching by considering GPS information of images and seam cutting algorithm. Our method develops an efficient approach to generate the flight path of UAV. We then select alternative images and calculate the overlapping region according to the distance between adjacent images. Features are efficiently detected not only in longitude overlap, but also in lateral, which largely improves stitching accuracy and decreases accumulative errors. In order to handle parallax caused by low altitude flight, we use seam finding method to avoid ghost. Experimental results show that our approach can effectively stitch a large number of images and successfully handle small parallax with low cost.

关键词： Aerial Image GPS Information Seam Cutting Image Registration Image Mosaic

来源：评论

学校读者我要写书评

暂无评论

Omni-supervised Facial Expression recognition via Distilled Data

arXiv

引用

arXiv 2020年

作者： Liu, Ping Wei, Yunchao Meng, Zibo Deng, Weihong Zhou, Joey Tianyi Yang, Yi Center for Frontier AI Research Agency for Science Technology and Research Singapore Singapore Institute of information science Beijing Jiaotong University Beijing China Centre for Artificial Intelligence University of Technology Sydney Sydney Australia Pattern Recognition and Intelligent System Laboratory Beijing University of Posts and Telecommunications Beijing China InnoPeak Technology Inc. Palo Alto United States

Facial expression plays an important role in understanding human emotions. Most recently, deep learning based methods have shown promising for facial expression recognition. However, the performance of the current state-of-the-art facial expression recognition (FER) approaches is directly related to the labeled data for training. To solve this issue, prior works employ the pretrain-and-finetune strategy, i.e., utilize a large amount of unlabeled data to pretrain the network and then finetune it by the labeled data. As the labeled data is in a small amount, the final network performance is still restricted. From a different perspective, we propose to perform omni-supervised learning to directly exploit reliable samples in a large amount of unlabeled data for network training. Particularly, a new dataset is firstly constructed using a primitive model trained on a small number of labeled samples to select samples with high confidence scores from a face dataset, i.e., MS-Celeb-1M [1], based on feature-wise similarity. We experimentally verify that the new dataset created in such an omni-supervised manner can significantly improve the generalization ability of the learned FER model. However, as the number of training samples grows, computational cost and training time increase dramatically. To tackle this, we propose to apply a dataset distillation strategy to compress the created dataset into several informative class-wise images, significantly improving the training efficiency. We have conducted extensive experiments on widely used benchmarks, where consistent performance gains can be achieved under various settings using the proposed framework. More importantly, the distilled dataset has shown its capabilities of boosting the performance of FER with negligible additional computational costs. We hope this work will serve as a solid baseline and help ease future research in FER. Copyright © 2020, The Authors. All rights reserved.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Mem Brain: An Easy-to-Use Online Webserver for Transmembrane Protein Structure Prediction

引用

Nano-Micro Letters 2018年第1期10卷 12-19页

作者： Xi Yin Jing Yang Feng Xiao Yang Yang Hong-Bin Shen Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Department of Computer Science Shanghai Jiao Tong University Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering

Membrane proteins are an important kind of proteins embedded in the membranes of cells and play crucial roles in living organisms, such as ion channels,transporters, receptors. Because it is difficult to determinate the membrane protein's structure by wet-lab experiments,accurate and fast amino acid sequence-based computational methods are highly desired. In this paper, we report an online prediction tool called Mem Brain, whose input is the amino acid sequence. Mem Brain consists of specialized modules for predicting transmembrane helices, residue–residue contacts and relative accessible surface area of a-helical membrane proteins. Mem Brain achieves aprediction accuracy of 97.9% of ATMH, 87.1% of AP,3.2 ± 3.0 of N-score, 3.1 ± 2.8 of C-score. Mem BrainContact obtains 62%/64.1% prediction accuracy on training and independent dataset on top L/5 contact prediction,respectively. And Mem Brain-Rasa achieves Pearson correlation coefficient of 0.733 and its mean absolute error of13.593. These prediction results provide valuable hints for revealing the structure and function of membrane *** Brain web server is free for academic use and available at ***/bioinf/Mem Brain/.

关键词： Transmembrane a-helices Structure prediction Machine learning Contact map prediction Relative accessible surface area

来源：评论

学校读者我要写书评

暂无评论

Research on Real-time Video Action Classification Based on Three-Dimensional Convolutional Neural Network

Research on Real-time Video Action Classification Based on T...

引用

IEEE International Conference on Network Infrastructure and Digital Content (IC-NIDC)

作者： Mingli Yu Chuang Zhang Ming Wu Pattern Recognition and Intelligent System Lab BUPT Beijing China

This paper describes a model for performing action classification in real-time video streaming. This model can simultaneously analyze the spatio-temporal information of video under the constraint of low delay. In addition, in order to prevent the model from judging motionless segments in the video as motion, the model in this article is equipped with the ability of distinguish the segments of motion from the stationary ones. The experimental results show that the model can complete the action classification task with little delay, which ensures that the classification result can be output in real time with the constant input of the video image.

关键词： Streaming media Optical flow Real-time systems Optical buffering Convolutional neural networks Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Efficient Algorithms for E-Healthcare to Solve Multiobject Fuse Detection Problem

引用

Journal of Healthcare Engineering 2021年 2021卷

作者： Ahmad, Ijaz Ullah, Inam Khan, Wali Ullah Ur Rehman, Ateeq Adrees, Mohmmed S. Saleem, Muhammad Qaiser Cheikhrouhou, Omar Hamam, Habib Shafiq, Muhammad School of Pattern Recognition and Intelligent System Shenzhen Institute of Advance Technology Chinese Academy of Science Shenzhen China Changzhou Campus Changzhou213022 China School of Information Science and Engineering Shandong University Qingdao266071 China Department of Electrical Engineering Government College University Lahore54000 Pakistan College of Computer Science and Information Technology Al Baha University Al Baha Saudi Arabia College of CIT Taif University P.O. Box 11099 Taif21944 Saudi Arabia Faculty of Engineering Université de Moncton MonctonNBE1A3E9 Canada Sfax Tunisia Department of Information and Communication Engineering Yeungnam University Gyeongsan38541 Korea Republic of

Object detection plays a vital role in the fields of computer vision, machine learning, and artificial intelligence applications (such as FUSE-AI (E-healthcare MRI scan), face detection, people counting, and vehicle detection) to identify good and defective food products. In the field of artificial intelligence, target detection has been at its peak, but when it comes to detecting multiple targets in a single image or video file, there are indeed challenges. This article focuses on the improved K-nearest neighbor (MK-NN) algorithm for electronic medical care to realize intelligent medical services and applications. We introduced modifications to improve the efficiency of MK-NN, and a comparative analysis was performed to determine the best fuse target detection algorithm based on robustness, accuracy, and computational time. The comparative analysis is performed using four algorithms, namely, MK-NN, traditional K-NN, convolutional neural network, and backpropagation. Experimental results show that the improved K-NN algorithm is the best model in terms of robustness, accuracy, and computational time. © 2021 Ijaz Ahmad et al.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Feature Fusion of Speech Emotion recognition Based on Deep Learning

Feature Fusion of Speech Emotion Recognition Based on Deep L...

引用

IEEE International Conference on Network Infrastructure and Digital Content (IC-NIDC)

作者： Gang Liu Wei He Bicheng Jin Pattern Recognition and Intelligent System Laboratory Beijing University of Posts and Telecommunications Beijing China

Speech emotion recognition (SER) is a hot topic in academia. One of the key issues in improving the performance of SER systems is the choice of speech emotion features. In order to establish a robust speech emotion recognition system, it is essential to select the features which can be a perfect representation of speech emotion attributes. Researchers has done a lot of work, proposed a variety of emotional features and made great progress. Although each kind of features were proven to be effective, most of methods are based on a single type. In this paper, we proposed a method of feature fusion based on deep learning, combining spectral-based features and pitch-based hyper-prosodic features. The experiments show that this method improves the performance of speech emotion recognition system.

关键词： Feature extraction Emotion recognition Speech recognition Hidden Markov models Acoustics Data mining

来源：评论

学校读者我要写书评

暂无评论

CNN-Based Audio Front End Processing on Speech recognition

CNN-Based Audio Front End Processing on Speech Recognition

引用

International Conference on Audio, Language and Image Processing, ICALIP

作者： Ruchao Fan Gang Liu Pattern Recognition and Intelligent System Laboratory Beijing University of Posts and Telecommunications Beijing China

Recently, Convolutional Neural Networks (CNNs) have become widely used in the field of speech recognition. Their role is to mitigate the spectral shifts caused by differences between the speakers and the environment. However, how to better use CNN for speech recognition has always been a problem worth exploring. This paper study the usage of CNN as the audio front end processing network based on the acoustic model architecture of Long Short-Term Memory and Connectionist Temporal Classification (LSTM-CTC). Firstly, by comparing the different inputs of the model, a Full-Mel Spectrogram feature that accords with the auditory characteristics is proposed. After determining the input features, this paper explores the principles of CNN parameters design and its role in speech recognition through the comparative experiments of different parameters. Finally, when decoding with phoneme-level language model, we achieve a test set error of 16.9% on the TIMIT phoneme recognition benchmark, which is the best known result of using the CTC as loss function.

关键词： Convolution Kernel Hidden Markov models Spectrogram Computer architecture Speech recognition Filter banks

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：