检索结果-内蒙古大学图书馆

Differentiable neural architecture learning for efficient neural network design

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Guo, Qingbei Wu, Xiao-Jun Kittler, Josef Feng, Zhiquan Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence Jiangnan University Wuxi214122 China Shandong Provincial Key Laboratory of Network based Intelligent Computing University of Jinan Jinan250022 China Centre for Vision Speech and Signal Processing University of Surrey GuildfordGU2 7XH United Kingdom

Automated neural network design has received ever-increasing attention with the evolution of deep convolutional neural networks (CNNs), especially involving their deployment on embedded and mobile platforms. One of the biggest problems that neural architecture search (NAS) confronts is that a large number of candidate neural architectures are required to train, using, for instance, reinforcement learning and evolutionary optimisation algorithms, at a vast computation cost. Even recent differentiable neural architecture search (DNAS) samples a small number of candidate neural architectures based on the probability distribution of learned architecture parameters to select the final neural architecture. To address this computational complexity issue, we introduce a novel architecture parameterisation based on scaled sigmoid function, and propose a general Differentiable Neural Architecture Learning (DNAL) method to optimize the neural architecture without the need to evaluate candidate neural networks. Specifically, for stochastic supernets as well as conventional CNNs, we build a new channel-wise module layer with the architecture components controlled by a scaled sigmoid function. We train these neural network models from scratch. The network optimization is decoupled into the weight optimization and the architecture optimization, which avoids the interaction between the two types of parameters and alleviates the vanishing gradient problem. We address the non-convex optimization problem of neural architecture by the continuous scaled sigmoid method with convergence guarantees. Extensive experiments demonstrate our DNAL method delivers superior performance in terms of neural architecture search cost, and adapts to conventional CNNs (e.g., VGG16 and ResNet50), lightweight CNNs (e.g., MobileNetV2) and stochastic supernets (e.g., ProxylessNAS). The optimal networks learned by DNAL surpass those produced by the state-of-the-art methods on the benchmark CIFAR-10 and imageN

关键词： Deep neural networks

Towards multimodal response generation with exemplar augmentation and curriculum optimization

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Lei, Zeyang Li, Zekang Zhang, Jinchao Meng, Fandong Feng, Yang Yang, Yujiu Niu, Cheng Zhou, Jie Tsinghua University China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Pattern Recognition Center WeChat AI Tencent Inc China

Recently, variational auto-encoder (VAE) based approaches have made impressive progress on improving the diversity of generated responses. However, these methods usually suffer the cost of decreased relevance accompanied by diversity improvements (Zhang et al., 2018b). In this paper, we propose a novel multimodal1 response generation framework with exemplar augmentation and curriculum optimization to enhance relevance and diversity of generated responses. First, unlike existing VAE-based models that usually approximate a simple Gaussian posterior distribution, we present a Gaussian mixture posterior distribution (i.e, multimodal) to further boost response diversity, which helps capture complex semantics of responses. Then, to ensure that relevance does not decrease while diversity increases, we fully exploit similar examples (exemplars) retrieved from the training data into posterior distribution modeling to augment response relevance. Furthermore, to facilitate the convergence of Gaussian mixture prior and posterior distributions, we devise a curriculum optimization strategy to progressively train the model under multiple training criteria from easy to hard. Experimental results on widely used SwitchBoard and DailyDialog datasets demonstrate that our model achieves significant improvements compared to strong baselines in terms of diversity and relevance. Copyright © 2020, The Authors. All rights reserved.

关键词： Curricula

Abnormal resting-state EEG power and impaired inhibition control in young smokers

学校读者我要写书评

暂无评论

Neuroscience Letters 2021年第0期761卷 136120-136120页

作者： Dong, Fang Li, Xiaojian Zhang, Yunmiao Jia, Shaodi Zhang, Shidi Xue, Ting Ren, Yan Lv, Xiaoqi Yuan, Kai Yu, Dahua Inner Mongolia Key Laboratory of Pattern Recognition and Intelligent Image Processing School of Information Engineering Inner Mongolia University of Science and Technology Baotou 014010 Inner Mongolia China College of Information Engineering Inner Mongolia University of Technology Hohhot 010051 Inner Mongolia China School of Life Science and Technology Xidian University Xi'an 710071 Shaanxi China

Exposure to nicotine during adolescence may cause neurophysiological changes and increase the risks of developing nicotine dependence;it can even lead to lifelong smoking. The intake of nicotine may also lead to abnormal patterns of oscillatory brain activity and inhibition control deficits. However, little is known about the specific relationship between oscillatory brain activity during the resting state and inhibition control capacity in young smokers. In the present study, we acquired resting-state electroencephalography (EEG) data from thirty-four young smokers and 39 age-matched non-smoking controls. Inhibition control performance was measured by a Go/NoGo task. Compared with non-smoking controls, we detected reduced low-frequency delta band activity in the frontal, central and posterior cortices of young smokers. Furthermore, young smokers committed more errors in response to infrequent NoGo trials. Notably, we demonstrated that delta absolute power in the frontal region was negatively correlated with NoGo errors and that alpha power in the central region was positively correlated with NoGo errors in non-smoking controls but not in young smokers. These findings may suggest that these inhibitory control processes were associated with alterations in oscillatory brain activity during the resting state. Our findings suggest that alterations of power spectra in delta bands may act as a useful biomarker of inhibitory control performance and provide a scientific basis for the diagnosis and treatment of nicotine addiction in adolescents. © 2021 Elsevier B.V.

关键词： Brain oscillations Electroencephalography (EEG) Inhibition control Resting state Young smokers

NTIRE 2023 image Shadow Removal Challenge Report

学校读者我要写书评

暂无评论

NTIRE 2023 Image Shadow Removal Challenge Report

2023 IEEE/CVF Conference on Computer Vision and pattern recognition Workshops, CVPRW 2023

作者： Vasluianu, Florin-Alexandru Seizinger, Tim Timofte, Radu Cui, Shuhao Huang, Junshi Tian, Shuman Fan, Mingyuan Zhang, Jiaqi Zhu, Li Wei, Xiaoming Wei, Xiaolin Luo, Ziwei Gustafsson, Fredrik K. Zhao, Zheng Sjölund, Jens Schön, Thomas B. Dong, Xiaoyi Zhang, Xi Sheryl Li, Chenghua Leng, Cong Yeo, Woon-Ha Oh, Wang-Taek Lee, Yeo-Reum Ryu, Han-Cheol Luo, Jinting Jiang, Chengzhi Han, Mingyan Wu, Qi Lin, Wenjie Yu, Lei Li, Xinpeng Jiang, Ting Fan, Haoqiang Liu, Shuaicheng Xu, Shuning Song, Binbin Chen, Xiangyu Zhang, Shile Zhou, Jiantao Zhang, Zhao Zhao, Suiyi Zheng, Huan Gao, Yangcheng Wei, Yanyan Wang, Bo Ren, Jiahuan Luo, Yan Kondo, Yuki Miyata, Riku Yasue, Fuma Naruki, Taito Ukita, Norimichi Chang, Hua-En Yang, Hao-Hsiang Chen, Yi-Chung Chiang, Yuan-Chun Huang, Zhi-Kai Chen, Wei-Ting Chen, I-Hsiang Hsieh, Chia-Hsuan Kuo, Sy-Yen Xianwei, Li Fu, Huiyuan Liu, Chunlin Ma, Huadong Fu, Binglan He, Huiming Wang, Mengjia She, Wenxuan Liu, Yu Nathan, Sabari Kansal, Priya Zhang, Zhongjian Yang, Huabin Wang, Yan Zhang, Yanru Phutke, Shruti S. Kulkarni, Ashutosh Khan, Md Raqib Murala, Subrahmanyam Vipparthi, Santosh Kumar Ye, Heng Liu, Zixi Yang, Xingyi Liu, Songhua Wu, Yinwei Jing, Yongcheng Yu, Qianhao Zheng, Naishan Huang, Jie Long, Yuhang Yao, Mingde Zhao, Feng Zhao, Bowen Ye, Nan Shen, Ning Cao, Yanpeng Xiong, Tong Xia, Weiran Li, Dingwen Xia, Shuchen Computer Vision Lab Ifi Caidas University of Würzburg Germany Computer Vision Lab Eth Zürich Switzerland Meituan Group China Department of Information Technology Uppsala University Sweden Institute of Automation Chinese Academy of Sciences Beijing China Nanjing China Maicro Nanjing China Department of Artificial Intelligence Convergence Sahmyook University Seoul Korea Republic of Megvii Technology China University of Electronic Science and Technology of China China University of Macau China China Toyota Technological Institute Japan Graduate Institute of Electronics Engineering National Taiwan University Taiwan Department of Electrical Engineering National Taiwan University Taiwan Graduate Institute of Communication Engineering National Taiwan University Taiwan ServiceNow United States Beijing University of Post and Teleconmunication Beijing China Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education China Couger Inc. Computer Vision and Pattern Recognition Lab Indian Institute of Technology Ropar Punjab Rupnagar India Research Institute Singapore National University of Singapore Singapore Research Institute Singapore University of Sydney Australia Brain-Inspired Vision Laboratory Information Science and Technology Institution University of Science and Technology of China China State Key Laboratory of Fluid Power and Mechatronic Systems School of Mechanical Engineering Zhejiang University Hangzhou310027 China Key Laboratory of Advanced Manufacturing Technology of Zhejiang Province School of Mechanical Engineering Zhejiang University Hangzhou310027 China South China University of Technology China

ISBN: (纸本)9798350302493

This work reviews the results of the NTIRE 2023 Challenge on image Shadow Removal. The described set of solutions were proposed for a novel dataset, which captures a wide range of object-light interactions. It consists of 1200 roughly pixel aligned pairs of real shadow free and shadow affected images, captured in a controlled environment. The data was captured in a white-box setup, using professional equipment for lights and data acquisition sensors. The challenge had a number of 144 participants registered, out of which 19 teams were compared in the final ranking. The proposed solutions extend the work on shadow removal, improving over the performance level describing state-of-the-art methods. © 2023 IEEE.

关键词： Data acquisition

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

学校读者我要写书评

暂无评论

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

Realization of Detection Algorithms for key Parts of Unmanned Aerial Vehicle Based on Deep Learning

学校读者我要写书评

暂无评论

Realization of Detection Algorithms for Key Parts of Unmanne...

International Conference on Wireless Communications and Signal processing (WCSP)

作者： Guangya Wang Hanyu Hong Yaozong Zhang Jinmeng Wu Yunfei Wang Shiyang Li Hubei Key Laboratory of Optical Information and Pattern Recognition School of Electrical and Information Engineering Wuhan Institute of Technology Wuhan China Hubei Engineering Research Center of Video Image and HD Projection

ISBN: (数字)9781728172361

ISBN: (纸本)9781728172378

Fixed-point attack on the key parts of small aerial vehicles is one of the important means of UAV (Unmanned Aerial Vehicle) countermeasure. Fixed-wing aircraft flying in the air has two characteristics: fast speed and fast attitude change of aircraft. However, the traditional detection method of key parts of fixed-wing aircraft in infrared images is not only slow in speed but also low in accuracy. This paper presents an improved target detection and motion tracking algorithm based on deep learning method. The algorithm uses a deeper neural network to enhance the feature extraction capabilities of CNN and obtain richer feature information. The detection algorithm obtains the position and motion direction of the key points of the target. Experimental results show that the detection algorithm proposed in this paper is up to 30 frame/s, with an average accuracy of 91.5%/. The method achieved good results in the experiment.

关键词： Feature extraction Aircraft Unmanned aerial vehicles Convolution Target recognition Prediction algorithms Object detection

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

学校读者我要写书评

暂无评论

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

CAMEL2: Enhancing weakly supervised learning for histopathology images by incorporating the significance ratio

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Xu, Gang Wang, Shuhao Zhao, Lingyu Chen, Xiao Wang, Tongwei Wang, Lang Luo, Zhenwei Wang, Dahan Zhang, Zewen Liu, Aijun Ba, Wei Song, Zhigang Shi, Huaiyin Zhong, Dingrong Ma, Jianpeng Multiscale Research Institute of Complex Systems Fudan University Shanghai China Zhangjiang Fudan International Innovation Center Fudan University Shanghai China Shanghai AI Laboratory Shanghai China Thorough Lab Thorough Future Beijing China Department of Pathology China-Japan Friendship Hospital Beijing China Minjiang University Fuzhou China College of Future Technology Peking University Beijing China Fujian Key Laboratory of Pattern Recognition and Image Understanding School of Computerand Information Engineering Xiamen University of Technology Xiamen China Department of Pathology Seventh Medical Center Chinese PLA General Hospital Beijing China Department of Pathology First Medical Center Chinese PLA General Hospital Beijing China

Histopathology image analysis plays a crucial role in cancer diagnosis. However, training a clinically applicable segmentation algorithm requires pathologists to engage in labour-intensive labelling. In contrast, weakly supervised learning methods, which only require coarse-grained labels at the image level, can significantly reduce the labeling efforts. Unfortunately, while these methods perform reasonably well in slide-level prediction, their ability to locate cancerous regions, which is essential for many clinical applications, remains unsatisfactory. Previously, we proposed CAMEL, which achieves comparable results to those of fully supervised baselines in pixel-level segmentation. However, CAMEL requires 1,280×1,280 image-level binary annotations for positive WSIs. Here, we present CAMEL2, by introducing a threshold of the cancerous ratio for positive bags, it allows us to better utilize the information, consequently enabling us to scale up the image-level setting from 1,280×1,280 to 5,120×5,120 while maintaining the accuracy. Our results with various datasets, demonstrate that CAMEL2, with the help of 5,120×5,120 image-level binary annotations, which are easy to annotate, achieves comparable performance to that of a fully supervised baseline in both instance- and slide-level classifications. © 2023, CC BY.

关键词： image enhancement

One-shot distributed algorithm for generalized eigenvalue problem

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Lyu, Kexin He, Fan Huang, Xiaolin Yang, Jie Chen, Liming Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University MOE Key Laboratory of System Control and Information Processing 800 Dongchuan Road Shanghai200240 China Institute of Medical Robotics Shanghai Jiao Tong University 800 Dongchuan Road Shanghai200240 China Ecole Centrale de Lyon France

Nowadays, more and more datasets are stored in a distributed way for the sake of memory storage or data privacy. The generalized eigenvalue problem (GEP) plays a vital role in a large family of high-dimensional statistical models. However, the existing distributed method for eigenvalue decomposition cannot be applied in GEP for the divergence of the empirical covariance matrix. Here we propose a general distributed GEP framework with one-shot communication for GEP. If the symmetric data covariance has repeated eigenvalues, e.g., in canonical component analysis, we further modify the method for better convergence. The theoretical analysis on approximation error is conducted and the relation to the divergence of the data covariance, the eigenvalues of the empirical data covariance, and the number of local servers is analyzed. Numerical experiments also show the effectiveness of the proposed algorithms. Copyright © 2020, The Authors. All rights reserved.

关键词： Eigenvalues and eigenfunctions