检索结果-内蒙古大学图书馆

International Conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Jyothi Rikhab Chand Mathews Jacob Department of Electrical and Computer Engineering University of Iowa IA USA Department of Electrical and Computer Engineering University of Virginia VA USA

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

We propose a multi-scale deep energy model that is strongly convex in the local neighbourhood around the data manifold to represent its probability density, with application in inverse problems. In particular, we represent the negative log-prior as a multi-scale energy model parameterized by a Convolutional neural Network (CNN). We restrict the gradient of the CNN to be locally monotone, which constrains the model as a Locally Convex Multi-Scale Energy (LC-MuSE). We use the learned energy model in image-based inverse problems, where the formulation offers several desirable properties: i) uniqueness of the solution, ii) convergence guarantees to a minimum of the inverse problem, and iii) robustness to input perturbations. In the context of parallel Magnetic Resonance (MR) image reconstruction, we show that the proposed method performs better than the state-of-the-art convex regularizers, while the performance is comparable to plug-and-play regularizers and end-to-end trained methods.

关键词： Manifolds Inverse problems Perturbation methods Magnetic resonance signal processing Robustness Data models Convolutional neural networks Speech processing image reconstruction

来源：评论

学校读者我要写书评

暂无评论

PID Controller-Inspired Model Design for Single image De-Raining

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS ii-EXPRESS BRIEFS 2022年第4期69卷 2351-2355页

作者： Zhou, Man Wang, Fan Wei, Xian Wang, Rujing Wang, Xue Chinese Acad Sci Inst Intelligent Machines Intelligent Agr Engn Lab Anhui Prov Hefei 230031 Peoples R China Chinese Acad Sci Hefei Inst Phys Sci Hefei 230031 Peoples R China Univ Sci & Technol China Hefei 230026 Peoples R China East China Normal Univ MOE Engn Res Ctr Software & Hardware Codesign & A Shanghai 200062 Peoples R China

Deep learning based methods have achieved remarkable breakthroughs on the single image de-raining task. However, most of the current models are constructed by empirically designing black-box network architectures. These network architectures always lack sufficient interpretability, which limits their further improvements in de-raining performance. In this brief, inspired by the classical Proportional Integral Derivative (PID) controller and feedback mechanism in the automatic control community, we propose a novel de-raining network architecture to address the above issues. Specifically, since the PID controller can speed up the system convergence and eliminate the system steady-state error, this motivates us to mimic the signal processing flow of PID controller to provide an interpretable and reliable guideline on de-raining network designs. By casting the signal flow process in the PID controller as blueprints, we extend the PID controller to an almost parameter-free network module, named PID-IM with every component in the module one-to-one corresponding to each operation involved in PID controller. Equipped with PID-IM, our proposed network could efficiently explore and exploit the features of rain streaks in a recursive fashion. Extensive experiments on several benchmarks demonstrate that our method has best performance over other de-raining methods. In addition, by directly embedding our PID-IM into existing baseline networks, the de-raining performance can be significantly improved.

关键词： Control theory single image de-raining neural network

来源：评论

学校读者我要写书评

暂无评论

Deep Learning and image Super-Resolution-Guided Beam and Power Allocation for mmWave Networks

引用

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY 2023年第11期72卷 15080-15085页

作者： Cao, Yuwen Ohtsuki, Tomoaki Maghsudi, Setareh Quek, Tony Q. S. Donghua Univ Shanghai 201620 Peoples R China Northwestern Polytech Univ Xian 710072 Peoples R China Keio Univ Yokohama 2238522 Japan Univ Tubingen D-72074 Tubingen Germany Fraunhofer Heinrich Hertz Inst D-10587 Berlin Germany Singapore Univ Technol & Design Singapore 487372 Singapore Yonsei Univ Yonsei Frontier Lab Seoul 03722 South Korea

In this article, we develop a deep learning (DL)-guided hybrid beam and power allocation approach for multiuser millimeter-wave (mmWave) networks, which facilitates swift beamforming at the base station (BS). The following persisting challenges motivated our research: (i) User and vehicular mobility, as well as redundant beam-reselections in mmWave networks, degrade the efficiency;(ii) Due to the large beamforming dimension at the BS, the beamforming weights predicted by the cutting-edge DL-based methods often do not suit the channel distributions;(iii) Co-located user devices may cause a severe beam conflict, thus deteriorating system performance. To address the aforementioned challenges, we exploit the synergy of supervised learning and super-resolution technology to enable low-overhead beam- and power allocation. In the first step, we propose a method for beam-quality prediction. It is based on deep learning and explores the relationship between high- and low-resolution beam images (energy). Afterward, we develop a DL-based allocation approach, which enables high-accuracy beam and power allocation with only a portion of the available time-sequential low-resolution images. Theoretical and numerical results verify the effectiveness of our proposed framework.

关键词： Array signal processing Millimeter wave communication Resource management Training neural networks Deep learning Downlink Deep learning power allocation temporal and spatial resolution mmWave networks super-resolution

来源：评论

学校读者我要写书评

暂无评论

stochastic Optimization of Vector Quantization methods in Application to Speech and image processing

Stochastic Optimization of Vector Quantization Methods in Ap...

引用

International Conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Mohammad Hassan Vali Tom Bäckström Department of Signal Processing and Acoustics Aalto University Finland

Vector quantization (VQ) methods have been used in a wide range of applications for speech, image, and video data. While classic VQ methods often use expectation maximization, in this paper, we investigate the use of stochastic optimization employing our recently proposed noise substitution in vector quantization technique. We consider three variants of VQ including additive VQ, residual VQ, and product VQ, and evaluate their quality, complexity and bitrate in speech coding, image compression, approximate nearest neighbor search, and a selection of toy examples. Our experimental results demonstrate the trade-offs in accuracy, complexity, and bitrate such that using our open source implementations and complexity calculator, the best vector quantization method can be chosen for a particular problem.

关键词： Additives Speech coding Vector quantization Bit rate Toy manufacturing industry neural networks Nearest neighbor methods

来源：评论

学校读者我要写书评

暂无评论

A stochastic approach for automated brain MRI segmentation

引用

IET image processing 2021年第3期15卷 735-745页

作者： Chatterjee, Pubali Sharma, Kaushik Das Chakrabarti, Amlan Univ Calcutta AK Choudhury Sch Informat Technol Kolkata W Bengal India Univ Calcutta Dept Appl Phys Kolkata W Bengal India

This paper presents an approach to segment lesions from brain magnetic resonance images in a fully automatic manner. The proposed idea leverages the strength of classical random walker algorithm and graph cut optimization technique in a single framework. We demonstrate that formulating a "prior" from a stochastic model can ameliorate the need of manually selected seed selection process in the random walker framework, thus making the algorithm fully automatic in a generic manner. By analytically solving a linear system of equations in the random walk process, initial labelling is an element of [0, 1] of each pixel in the image are computed to obtain the likelihood probability. These probabilities are then used to compute the likelihood for the data fidelity term in the energy function to compute the final segmentation, which is minimized by min cut max flow algorithm. Experimental results show the superiority of the proposed method over the state-of-the-art techniques on publicly available datasets.

关键词： Algebra, set theory, and graph theory Probability theory, stochastic processes, and statistics Biophysics of neurophysiological processes Medical magnetic resonance imaging and spectroscopy Patient diagnostic methods and instrumentation Other topics in statistics Combinatorial mathematics Optical, image and video signal processing Biomedical magnetic resonance imaging and spectroscopy Other topics in statistics Combinatorial mathematics Computer vision and image processing techniques Biology and medical computing

来源：评论

学校读者我要写书评

暂无评论

LOCALLY OPTIMAL DETECTION OF stochastic TARGETED UNIVERSAL ADVERSARIAL PERTURBATIONS

LOCALLY OPTIMAL DETECTION OF STOCHASTIC TARGETED UNIVERSAL A...

引用

IEEE International Conference on Acoustics, Speech and signal processing (ICASSP)

作者： Goel, Amish Moulin, Pierre Univ Illinois Dept Elect & Comp Engn Urbana IL 61801 USA

ISBN: (纸本)9781728176055

Deep learning image classifiers are known to be vulnerable to small adversarial perturbations of input images. In this paper, we derive the locally optimal generalized likelihood ratio test based detector for detecting stochastic targeted universal adversarial perturbations to a classifier's input. We employ a two-stage process to learn the detector's parameters, which involves unsupervised maximum likelihood estimation followed by supervised training and demonstrates better performance of the detector compared to other detection methods on several popular image classification datasets.

关键词： image classification neural networks Locally optimal tests Universal adversarial perturbations

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of First Order Optimizers for Plant Pest Detection Using Deep Learning 4th

Performance Analysis of First Order Optimizers for Plant Pes...

引用

4th International Conference on Machine Learning, image processing, Network Security and Data Sciences (MIND)

作者： Saranya, T. Deisy, C. Sridevi, S. Muthu, Kalaiarasi Sonai Khan, M. K. A. Ahamed Thiagarajar Coll Engn Madurai Tamil Nadu India Multimedia Univ Melaka Malaysia UCSI Univ Kuala Lumpur Malaysia

ISBN: (纸本)9783031243660;9783031243677

Several of the major issues affecting food productivity are a pest. The timely and precise detection of plant pests is crucial for avoiding the loss of agricultural productivity. Only by detecting the pest at an early stage can it be controlled. Due to the cyclical nature of agriculture, pest accumulation and variety might vary from season to season, rendering standard approaches for pest classification and detection ineffective. methods based on machine learning can be utilized to resolve such issues. Deep Learning, which has become extremely popular in image processing, has recently opened up a plethora of new applications for smart agriculture. Optimizers are primarily responsible for the process of strengthening the deep learning model's pest detection capabilities. In order to detect pests on tomato plants, this study compares the performance of a few gradient-based optimizers, including stochastic gradient descent, root means square propagation, adaptive gradient, and adaptive moment estimation, on a proposed deep convolution neural network architecture with augmented data. In comparison to other optimizers, the evaluation findings demonstrate that the Adam optimizer performs better with an accuracy of 93% for pest identification.

关键词： Deep Learning Optimizers Convolution neural Network

来源：评论

学校读者我要写书评

暂无评论

Deep Sub-image Sampling Based Defense Against Spatial-Domain Adversarial Steganography

Deep Sub-Image Sampling Based Defense Against Spatial-Domain...

引用

Acoustics, Speech, and signal processing Workshops (ICASSPW), IEEE International Conference on

作者： Xinyu Huang Yuwen Cao Tomoaki Ohtsuki School of Cybersecurity Northwestern Polytechnical University Xi’an China College of Information Science and Technology Donghua University China Department of Information and Computer Science Keio University Japan

ISBN: (数字)9798350374513

ISBN: (纸本)9798350374520

Deep steganalyzer combined with neural networks has achieved great success in image classification over recent years. However, it suffers from the following persistent challenges: i) Deep steganalyzer is extremely vulnerable and has the risk of being attacked via adversarial steganography when performing the image classification tasks; ii) Pre-processing based methods aiming to remove adversarial perturbations from cover images jeopardize the accuracy performance, as the involved steganographic signal will be wiped off as well. In this context, to defend against adversarial attacks by an adversary, we propose an adversarial steganography detection scheme based on the pre-processing and feature migration. In brief, sub-images are sampled to obtain the dimensionality of the extracted features, which are usually used to expand them while reducing the effect brought by adversarial perturbations. In particular, by computing statistical features together with normalizing the features, our approach can improve the classification accuracy of the samples. Our experimental results show that the proposed approach is capable of detecting adversarial steganographic image with an accuracy gain of up to 35.9% over the state-of-the-art methods.

关键词： Steganography Accuracy Perturbation methods Conferences neural networks signal processing Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Comprehensive Electric load forecasting using ensemble machine learning methods 29

Comprehensive Electric load forecasting using ensemble machi...

引用

29th International Conference on Systems, signals and image processing (IWSSIP)

作者： Bhatnagar, Mansi Dwivedi, Vivek Singh, Divyanshu Rozinaj, Gregor Slovak Univ Technol FEI Dept Multimedia & Telecommun Bratislava Slovakia Blue Bricks Pvt Ltd AI ML Developer Lucknow India

ISBN: (数字)9781665495783

ISBN: (纸本)9781665495783

The accuracy of electric load forecasting is crucial when working on applications in power grid decision-making and operation. Due to the non-linear and stochastic behaviour of customers, the electric load profile is a complicated signal. In this paper, authors propose machine learning based automated system for electricity load forecasting, taking into consideration various variable factors that have an impact on the future electricity load demand. Three machine learning algorithms are used for evaluation of the proposed framework. The algorithms are evaluated on electricity load data collected from eastern region of Ontario, integrated with the weather and population data of the region. The Light GBM algorithm comparatively performs best with mean absolute error of 0.156. The developed system can be used for more accurate and efficient load forecasting applications.

关键词： Time series Machine learning ensemble learning Electricity load prediction

来源：评论

学校读者我要写书评

暂无评论

Local signal Adaptivity: Provable Feature Learning in neural Networks Beyond Kernels 35

Local Signal Adaptivity: Provable Feature Learning in Neural...

引用

35th Annual Conference on neural Information processing Systems (NeurIPS)

作者： Karp, Stefani Winston, Ezra Li, Yuanzhi Singh, Aarti Carnegie Mellon Univ Pittsburgh PA 15213 USA Google Res Mountain View CA 94043 USA

ISBN: (纸本)9781713845393

neural networks have been shown to outperform kernel methods in practice (including neural tangent kernels). Most theoretical explanations of this performance gap focus on learning a complex hypothesis class;in some cases, it is unclear whether this hypothesis class captures realistic data. In this work, we propose a related, but alternative, explanation for this performance gap in the image classification setting, based on finding a sparse signal in the presence of noise. Specifically, we prove that, for a simple data distribution with sparse signal amidst high-variance noise, a simple convolutional neural network trained using stochastic gradient descent simultaneously learns to threshold out the noise and find the signal. On the other hand, the corresponding neural tangent kernel, with a fixed set of predetermined features, is unable to adapt to the signal in this manner. We supplement our theoretical results by demonstrating this phenomenon empirically: in CIFAR-10 and MNIST images with various backgrounds, as the background noise increases in intensity, a CNN's performance stays relatively robust, whereas its corresponding neural tangent kernel sees a notable drop in performance. We therefore propose the local signal adaptivity (LSA) phenomenon as one explanation for the superiority of neural networks over kernel methods.

关键词： Gradient methods

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：