检索结果-内蒙古大学图书馆

Generative Adversarial Networks for Image Super-Resolution: A Survey

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Tian, Chunwei Zhang, Xuanyu Zhu, Qi Zhang, Bob Lin, Jerry Chun-Wei School of Software Northwestern Polytechnical University the National Engineering Laboratory for Integrated Aero-space-Ground-Ocean Big Data Application Technology 1 Dongxiang Rd Shaanxi Xi’an710129 China School of Software Northwestern Polytechnical University 1 Dongxiang Rd Shaanxi Xi’an710129 China College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics 101 Section 2 Kuang-Fu Road Jiangsu Nanjing China PAMI Research Group University of Macau 101 Section 2 Kuang-Fu Road Macao999078 China Department of Computer Science Western Norway University of Applied Sciences Bergen Norway

Single image super-resolution (SISR) has played an important role in the field of image processing. Recent generative adversarial networks (GANs) can achieve excellent results on low-resolution images with small samples. However, there are little literatures summarizing different GANs in SISR. In this paper, we conduct a comparative study of GANs from different perspectives. We first take a look at developments of GANs. Second, we present popular architectures for GANs in big and small samples for image applications. Then, we analyze motivations, implementations and differences of GANs based optimization methods and discriminative learning for image super-resolution in terms of supervised, semi-supervised and unsupervised manners, where these GANs are analyzed via integrating different network architectures, prior knowledge, loss functions and multiple tasks. Next, we compare performance of these popular GANs on public datasets via quantitative and qualitative analysis in SISR. Finally, we highlight challenges of GANs and potential research points for SISR. © 2022, CC BY-NC-ND.

关键词： Generative adversarial networks

Image Segmentation Using Background Subtraction On Colored Images

学校读者我要写书评

暂无评论

Image Segmentation Using Background Subtraction On Colored I...

International Conference on Opto-Electronics and Applied Optics (IEM OPTRONIX)

作者： Arunabha Tarafdar Sukanya Roy Anurup Mondal Rupsa Sen Arpan Adhikari Computer Science & Engineering University Of Engineering and Management Kolkata India Masters Of Computer Application University Of Engineering and Management Kolkata India

This paper on object detection by image processing to ensure the people suffering from various vision disorders to detect and to perceive the real image before them. The image perceived by the patients are rendered and developed so that the closest similar object is detected. The input to the program is a image which is fed to the set of processes which in turn gives a image that can be compared to the set of data to give the accuracy in (percentage) to which extend the image is similar to an object or animal.

关键词： Image color analysis Image segmentation Color Filtering algorithms computer applications computer science

USEV: Universal Speaker Extraction with Visual Cue

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Pan, Zexu Ge, Meng Li, Haizhou The Integrative Sciences and Engineering Programme The Institute of Data Science The Department of Electrical and Computer Engineering National University of Singapore 119077 Singapore The Department of Electrical and Computer Engineering National University of Singapore 119077 Singapore The Tianjin Key Laboratory of Cognitive Computing and Application College of Intelligence and Computing Tianjin University Tianjin300072 China The School of Data Science The Chinese University of Hong Kong Shenzhen518172 China The University of Bremen 28359 Germany Kriston AI Xiamen China

A speaker extraction algorithm seeks to extract the target speaker's speech from a multi-talker speech mixture. The prior studies focus mostly on speaker extraction from a highly overlapped multi-talker speech mixture. However, the target-interference speaker overlapping ratios could vary over a wide range from 0% to 100% in natural speech communication, furthermore, the target speaker could be absent in the speech mixture, the speech mixtures in such universal multi-talker scenarios are described as general speech mixtures. The speaker extraction algorithm requires an auxiliary reference, such as a video recording or a pre-recorded speech, to form top-down auditory attention on the target speaker. We advocate that a visual cue, i.e., lip movement, is more informative than an audio cue, i.e., pre-recorded speech, to serve as the auxiliary reference for speaker extraction in disentangling the target speaker from a general speech mixture. In this paper, we propose a universal speaker extraction network with a visual cue, that works for all multi-talker scenarios. In addition, we propose a scenario-aware differentiated loss function for network training, to balance the network performance over different target-interference speaker pairing scenarios. The experimental results show that our proposed method outperforms various competitive baselines for general speech mixtures in terms of signal fidelity. Copyright © 2021, The Authors. All rights reserved.

关键词： Mixtures

Hyper-Parameter-Free Latent Factor Analysis via Adaptive Moment Estimation-Incorporated Particle Swarm Optimization

学校读者我要写书评

暂无评论

Hyper-Parameter-Free Latent Factor Analysis via Adaptive Mom...

Cyber-Physical Social Intelligence (ICCSI), International Conference on

作者： Jiufang Chen Ye Yuan Chunlin He School of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing China Chinese Academy of Sciences Chongqing Institute of Green and Intelligent Technology Chongqing China Chongqing School University of Chinese Academy of Sciences Chongqing China Chongqing Key Laboratory of Big Data and Intelligent Computing Chongqing Engineering Research Center of Big Data Application for Smart Cities Chongqing China School of Computer Science China West Normal University Nanchong Sichuan China

ISBN: (纸本)9781665426220

A latent factor analysis (LFA) model can efficiently address a high-dimensional and sparse (HiDS) matrix with a stochastic gradient descent (SGD) algorithm. However, an SGD-based LFA model's performance depends heavily on its hyper-parameters. The popular method is based on grid-search, which fails because of expensive computation and time-consuming. Aiming at implementing a hyper-parameter-free LFA model, this study proposes an adaptive moment estimation-incorporated particle swarm optimization (Adam-PSO) algorithm that efficiently addresses the premature issues in a PSO algorithm. With achieved the hyper-parameter adaptation in an SGD-based LFA model, an Adam-PSO-based LFA (APL) model possessing hyper-parameter-free training is further implemented. Empirical studies on four HiDS matrices indicate that compared with state-of-the-art models with hyper-parameter adaptation settings, an APL model achieves the most efficient hyper-parameter-free training and highly competitive prediction accuracy for missing data of an HiDS matrix. Hence, it fits the need of real applications with high scalability and efficiency.

关键词： Training Adaptation models Computational modeling Stochastic processes Predictive models Prediction algorithms Data models

DENOISED INTERNAL MODELS: A BRAIN-INSPIRED AUTOENCODER AGAINST ADVERSARIAL ATTACKS

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Liu, Kaiyuan Li, Xingyu Lai, Yurui Zhang, Ge Su, Hang Wang, Jiachen Guo, Chunxu Xie, Hong Guan, Ji-Song Zhou, Yi School of Life Sciences and Technology ShanghaiTech University China Shanghai Center for Brain Science and Brain-Inspired Technology China School of Life Sciences Tsinghua University China National Engineering Laboratory for Brain-inspired Intelligence Technology and Application School of Information Science and Technology University of Science and Technology of China China Institute of Photonic Chips University of Shanghai for Science and Technology China Centre for Artificial-Intelligence Nanophotonics School of Optical-Electrical and Computer Engineering University of Shanghai for Science and Technology China

Despite its great success, deep learning severely suffers from robustness;that is, deep neural networks are very vulnerable to adversarial attacks, even the simplest ones. Inspired by recent advances in brain science, we propose the Denoised Internal Models (DIM), a novel generative autoencoder-based model to tackle this challenge. Simulating the pipeline in the human brain for visual signal processing, DIM adopts a two-stage approach. In the first stage, DIM uses a denoiser to reduce the noise and the dimensions of inputs, reflecting the information pre-processing in the thalamus. Inspired from the sparse coding of memory-related traces in the primary visual cortex, the second stage produces a set of internal models, one for each category. We evaluate DIM over 42 adversarial attacks, showing that DIM effectively defenses against all the attacks and outperforms the SOTA on the overall robustness. Copyright © 2021, The Authors. All rights reserved.

关键词： Deep neural networks

Heterogeneous two-Stream Network with Hierarchical Feature Prefusion for Multispectral Pan-Sharpening

学校读者我要写书评

暂无评论

Heterogeneous two-Stream Network with Hierarchical Feature P...

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Dong Wang Yunpeng Bai Bendu Bai Chanyue Wu Ying Li National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer Science Northwestern Polytechnical University Xi'an China School of Communication and Information Engineering Xi’an University of Posts and Telecommunications Xi'an China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Shaanxi Provincial Key Laboratory of Speech & Image Information Processing Northwestern Polytechnical University Xi'an China

ISBN: (纸本)9781728176055;9781728176062

Multispectral (MS) pan-sharpening aims at producing a high spatial resolution (HR) MS image by fusing a single-band HR panchromatic (PAN) image and a corresponding MS image with low spatial resolution. In this paper, we propose a heterogeneous two-stream network (HTSNet) with hierarchical feature prefusion for MS pan-sharpening. The HTSNet employs a heterogeneous group of spatial and spectral streams for spatial and spectral information extraction, respectively. The spatial stream utilizes a 2D CNN for spatial information extraction from the PAN images, and the spectral stream obtains spectral feature cubes from the MS images by a 3D CNN. At the same time, a prefusion module is introduced to prefuse the spatial details with spectral information and transfer information between different streams, which can enhance later processing. In the experiment, the Gaofen-2 satellite dataset is utilized to compare the proposed method with the state-of-the-art MS pan-sharpening methods. Experimental results demonstrate the superiority of our HTSNet in terms of visual effect and quantitative qualities.

关键词： Satellites Three-dimensional displays Fuses Streaming media Signal processing Information retrieval Visual effects

Hyperspectral Unmixing Based on Nonnegative Matrix Factorization: A Comprehensive Review

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Feng, Xin-Ru Li, Heng-Chao Wang, Rui Du, Qian Jia, Xiuping Plaza, Antonio School of Information Science and Technology Southwest Jiaotong University Chengdu611756 China National Engineering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University Chengdu611756 China Department of Electrical and Computer Engineering Mississippi State University Mississippi State MS39762 United States School of Engineering and Information Technology University of New South Wales CanberraACT2612 Australia Hyperspectral Computing Laboratory Department of Technology of Computers and Communications Escuela Politécnica University of Extremadura Cáceres10071 Spain

Hyperspectral unmixing has been an important technique that estimates a set of endmembers and their corresponding abundances from a hyperspectral image (HSI). Nonnegative matrix factorization (NMF) plays an increasingly significant role in solving this problem. In this article, we present a comprehensive survey of the NMF-based methods proposed for hyperspectral unmixing. Taking the NMF model as a baseline, we show how to improve NMF by utilizing the main properties of HSIs (e.g., spectral, spatial, and structural information). We categorize three important development directions including constrained NMF, structured NMF, and generalized NMF. Furthermore, several experiments are conducted to illustrate the effectiveness of associated algorithms. Finally, we conclude the article with possible future directions with the purposes of providing guidelines and inspiration to promote the development of hyperspectral unmixing. Copyright © 2022, The Authors. All rights reserved.

关键词： Deep learning

Cloud-Magnetic Resonance Imaging System: In the Era of 6G and Artificial Intelligence

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhou, Yirong Wu, Yanhuang Su, Yuhan Li, Jing Cai, Jianyun You, Yongfu Guo, Di Qu, Xiaobo The Department of Electronic Science Biomedical Intelligent Cloud R&D Center Fujian Provincial Key Laboratory of Plasma and Magnetic Resonance National Institute for Data Science in Health and Medicine Institute of Artificial Intelligence Xiamen University Xiamen361104 China The Department of Electronic Science Key Laboratory of Digital Fujian on IoT Communication Architecture and Safety Technology Xiamen University Xiamen361104 China Shanghai Electric Group CO. LTD Shanghai200001 China China Telecom Group Quanzhou362000 China China Mobile Group Xiamen361005 China School of Computer and Information Engineering Fujian Engineering Research Center for Medical Data Mining and Application Xiamen University of Technology Xiamen361024 China

Magnetic Resonance Imaging (MRI) plays an important role in medical diagnosis, generating petabytes of image data annually in large hospitals. This voluminous data stream requires a significant amount of network bandwidth and extensive storage infrastructure. Additionally, local data processing demands substantial manpower and hardware investments. Data isolation across different healthcare institutions hinders cross-institutional collaboration in clinics and research. In this work, we anticipate an innovative MRI system and its four generations that integrate emerging distributed cloud computing, 6G bandwidth, edge computing, federated learning, and blockchain technology. This system is called Cloud-MRI, aiming at solving the problems of MRI data storage security, transmission speed, AI algorithm maintenance, hardware upgrading, and collaborative work. The workflow commences with the transformation of k-space raw data into the standardized Imaging Society for Magnetic Resonance in Medicine Raw Data (ISMRMRD) format. Then, the data are uploaded to the cloud or edge nodes for fast image reconstruction, neural network training, and automatic analysis. Then, the outcomes are seamlessly transmitted to clinics or research institutes for diagnosis and other services. The Cloud-MRI system will save the raw imaging data, reduce the risk of data loss, facilitate inter-institutional medical collaboration, and finally improve diagnostic accuracy and work efficiency. Copyright © 2023, The Authors. All rights reserved.

关键词： Magnetic resonance imaging

Tailored sandwich structures in all-organic dielectric composite to optimize energy storage performance

学校读者我要写书评

暂无评论

Journal of Energy Storage 2025年 130卷

作者： Yue Zhang Yue Wang Xin He Guowei Hao Zheng Gong Changhai Zhang Yongquan Zhang Tiandong Zhang Huajie Yi Qi Wang Key Laboratory of Engineering Dielectrics and Its Application Ministry of Education Harbin University of Science and Technology Harbin 150080 PR China School of Electrical and Electronic Engineering Harbin University of Science and Technology Harbin 150080 PR China School of Electronics and Computer Science University of Southampton Southampton SO17 1BJ UK Singapore Institute of Manufacturing Technology (SIMTech) Agency for Science Technology and Research (A*STAR) Singapore 636732 Singapore

Polymer-based dielectric capacitor is essential in modern electronic and power system due to the high dielectric constant, flexibility, and longevity. Yet, the progress is impeded by low energy storage density and efficiency. Here, this work introduces a novel, all-organic dielectric composite strategy that combines the high polarization strength of polyvinylidene fluoride (PVDF) with the superior insulation of linear dielectrics, specifically, polyethersulfone (PESU), polyimide (PI), and polymethylmethacrylate (PMMA). By investigating heterogeneous material compatibility and designing sandwich structure, the breakdown strength of composite is enhanced and the dielectric loss of it is minimized. Notably, a 30 wt% PMMA-PVDF composite exhibits a maximum energy storage density of 11.3 J/cm 3 at 531.5 kV/mm and a charge-discharge efficiency of 63.1 %. Moreover, sandwich-structured composites further improve performance, with a PMMA/30 wt% PMMA-PVDF/PMMA configuration achieving 11.6 J/cm 3 at 541.2 kV/mm and an efficiency of 70.1 %. This work demonstrates a promising route to overcome the intrinsic limitations of conventional dielectric materials, paving the way for advanced capacitor technologies.

关键词：