检索结果-内蒙古大学图书馆

6th International conference on Electronics and Electrical Engineering Technology (EEET)

作者： Sun, Ximin Jia, Jiangkai Zhang, Bin Hao, Yi Zheng, Bin Sun, Bo Li, Zihao Li, Yong State Gride Ecommerce Technol Co Ltd Tianjin Peoples R China

ISBN: (纸本)9798350395600;9798350395594

Face recognition technology has a wide range of application prospects, and important application value in content-based retrieval, digital video processing and visual detection. However, the noise in the process of image acquisition will directly affect the recognition ability of face image, and the stochastic resonance theory can convert the specific intensity of noise signal energy into useful signals. Therefore, this paper proposes an image processed method based on adaptive bidimensional empirical mode decomposition (BEMD) and stochastic resonance (SR) theory is used to improve the quality of noised face images. The noised face image is decomposed by adaptive BEMD algorithm, and multiple Intrinsic mode function (IMF) components and residual are obtained. The three IMF components containing the least feature information are selected and deleted by threshold parameters. After the remaining IMFs and the residual is reconstructed, the noise energy is transferred to the image features by SR. Meanwhile, the optimal parameters of the two-dimensional stochastic resonance system are automatically obtained by taking the Peak signal to noise ratio (PSNR) as the detection index, so as to realize the quality of the face image. Four different methods are used to improve 50 face images with glasses and 50 face images without glasses. Compared with the BEMD algorithm, median filter and mean filter, the face image data set improved by the method proposed in this paper has the highest PSNR, which improves the image quality.

关键词： bidimensional empirical mode decomposition stochastic resonance face image denoising

来源：评论

学校读者我要写书评

暂无评论

SRFAMap: A Method for Mapping Integrated Gradients of a CNN Trained with statistical Radiomic Features to Medical image Saliency Maps 2nd

SRFAMap: A Method for Mapping Integrated Gradients of a CNN ...

引用

2nd World conference on Explainable Artificial Intelligence (xAI)

作者： Davydko, Oleksandr Pavlov, Vladimir Biecek, Przemyslaw Longo, Luca Technol Univ Dublin Sch Comp Sci Artificial Intelligence & Cognit Load Res Lab Dublin Ireland Natl Tech Univ Ukraine Igor Sikorsky Kyiv Polytech Inst Kiev Ukraine Warsaw Univ Technol Warsaw Poland

ISBN: (纸本)9783031638022;9783031638039

Many explainable AI methods for generating medical image saliency maps exist, but most are devoted to working on trained neural network-based models. At the same time, many medical image classification neural networks use as input radiomic features derived from images. The mathematics for radiomic feature computations are not always represented by a differentiable function, which makes it impossible to apply existing saliency map methods to obtain input image pixel attributions because they heavily rely on gradient calculation possibility. For this reason, a novel method (SRFAMap) is introduced to map the statistical radiomic feature attributions derived by applying the Integrated Gradients methods, often used in explainable AI, to image saliency maps. In detail, integrated gradients are used to compute radiomic feature attributions of chest X-ray scans for a ResNet-50 convolutional network model trained to distinguish healthy lungs from tuberculosis lesions. These are subsequently mapped to saliency maps over the original scans to facilitate their interpretation for diagnostics. Findings show that, in most cases, SRFAMap can generate saliency maps with an acceptable level of faithfulness. The increase-in-confidence metric reached at least 34%, while the Average Drop reached 38% at most. Finally, the percentage of the statistically significant target class score increases reached at least 71% on 20 random folds for the grey-level co-occurrence matrix and higher for other methods when only pixels under positive saliency map values were revealed on the blurred image. The main contribution is a method of mapping integrated gradients to saliency maps to facilitate the visual interpretation of the relevant statistical radiomic features of X-ray scans of lungs responsible for discriminating types of lesions.

关键词： Explainable artificial intelligence Radiomics Texture analysis Medical image processing Saliency map

来源：评论

学校读者我要写书评

暂无评论

Matching the statistical Query Lower Bound for k-Sparse Parity Problems with Sign stochastic Gradient Descent 38

Matching the Statistical Query Lower Bound for k-Sparse Pari...

引用

38th conference on Neural Information processing Systems, NeurIPS 2024

作者： Kou, Yiwen Gu, Quanquan Chen, Zixiang Kakade, Sham M. Department of Computer Science University of California Los Angeles Los AngelesCA90095 United States Kempner Institute at Harvard University Harvard University CambridgeMA02138 United States

The k-sparse parity problem is a classical problem in computational complexity and algorithmic theory, serving as a key benchmark for understanding computational classes. In this paper, we solve the k-sparse parity problem with sign stochastic gradient descent, a variant of stochastic gradient descent (SGD) on two-layer fully-connected neural networks. We demonstrate that this approach can efficiently solve the k-sparse parity problem on a d-dimensional hypercube (k ≤ O(√d)) with a sample complexity of (eq)(dk−1) using 2Θ(k) neurons, matching the established Ω(dk) lower bounds of statistical Query (SQ) models2. Our theoretical analysis begins by constructing a good neural network capable of correctly solving the k-parity problem. We then demonstrate how a trained neural network with sign SGD can effectively approximate this good network, solving the k-parity problem with small statistical errors. To the best of our knowledge, this is the first result that matches the SQ lower bound for solving k-sparse parity problem using gradient-based methods. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optical-Infrared image Translation Based on Diffusion Models

Optical-Infrared Image Translation Based on Diffusion Models

引用

2024 conference on Spectral Technology and Applications, CSTA 2024

作者： Zhao, Yuxin Gao, Zihao Liao, Huaizhang Han, Tao Xia, Jingyuan College of Science National University of Defense Technology Hunan Changsha China College of Electronic Science National University of Defense Technology Hunan Changsha China

ISBN: (纸本)9781510683082

In the realms of computer vision and image processing, image-to-image translation is pivotal to data augmentation. Due to the high cost of hardware for direct registration of optical and infrared images and the limitations of conventional model-driven approaches in cross-domain registration, this paper focuses on generating infrared images from optical images using generative models. Existing image translation methods often treat target domain images as conditions, leading to inefficiencies. We propose a diffusion-based method for translating optical images to infrared. Using VQ-VAE for latent space formation and a bidirectional stochastic Brownian Bridge diffusion process for modal alignment, we validate its effectiveness through extensive simulations, showing superior performance compared to existing methods. © 2024 SPIE.

关键词： Infrared imaging

来源：评论

学校读者我要写书评

暂无评论

A statistical Approach to stochastic Computing Design and Analysis

A Statistical Approach to Stochastic Computing Design and An...

引用

作者： Baker, Timothy University of Michigan

学位级别：博士

stochastic computing (SC) is an unconventional computing style that uses probabilistic bitstreams to implement algorithms like those for machine learning, digital filtering, and image processing. SC's unusual encoding enables highly fault tolerant, low power, and small datapaths. For instance, a single AND gate performs multiplication in SC. SC's advantages make it attractive for use in small devices like wearables and biomedical implants, but widespread adoption of SC has been limited due to challenges including a steep accuracy-latency trade-off and expensive interface circuits. We address these challenges using a statistical approach. First, we develop a better framework for analyzing stochastic circuit errors and then use insights from statistical analysis to design and evaluate smaller and more accurate *** SC's many error sources is key to developing more accurate designs. However, existing approaches to accuracy analysis fail to provide a comprehensive account of all error types. The first part of this thesis proposes a novel framework named Bayesian Analysis of stochastic Errors (BASE). BASE is built on statistical estimation theory and identifies three key quantities that must be modeled or estimated to quantify a circuit's accuracy. BASE is used to better understand and address circuit errors and is compatible with prior methods for error analysis as well as new models that we propose in this thesis. Importantly, BASE reduces the reliance on black box simulation methods which provide limited insight and are prone to ***'s low-cost multipliers make it attractive for neural network and digital filtering applications. However, accurate addition is difficult to implement in SC and overhead from SC's data conversion circuits reduces SC's advantage for these applications. We address these problems by using insights from statistical modeling to develop new and better SC designs. Three such designs are introduced: 1) CeMux, a multiplexer

关键词：

来源：评论

学校读者我要写书评

暂无评论

FL0C: FAST L0 CUT PURSUIT FOR ESTIMATION OF PIECEWISE CONSTANT FUNCTIONS 29

FL0C: FAST L0 CUT PURSUIT FOR ESTIMATION OF PIECEWISE CONSTA...

引用

IEEE International conference on image processing (ICIP)

作者： Goerlitz, Andreas Moeller, Michael Kolb, Andreas Univ Siegen Comp Graph & Multimedia Grp Siegen Germany Univ Siegen Comp Vis Grp Siegen Germany

ISBN: (数字)9781665496209

ISBN: (纸本)9781665496209

Partitioning of images is a fundamental image processing task, which is closely related to various problems and applications in computer vision. Due to the hard nature of the underlying problem, existing algorithms are very compute intense. In this work we present a stochastic algorithm to efficiently approximate solutions of the image partitioning problem. Our contributions lie in the novel convex reformulation of the underlying graph cut problem, along with the application of a stochastic solver. These changes allow a faster convergence compared to other graph cut based methods, which is confirmed by our experiments.

关键词： image Partitioning Total Variation Cut Pursuit image Segmentation Piecewise Constant Mumford Shah

来源：评论

学校读者我要写书评

暂无评论

LEARNING HYBRID NEGATIVE PROBABILITY MODEL FOR WEAKLY-SUPERVISED WHOLE SLIDE image RECOGNITION 49

LEARNING HYBRID NEGATIVE PROBABILITY MODEL FOR WEAKLY-SUPERV...

引用

49th IEEE International conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Qiu, Yining Li, Yuxi Wu, Jiafu Gan, Zhenye Chi, Mingmin Wang, Yabiao Wang, Chengjie Wang, Pei Fudan Univ Shanghai key Lab data Sci Sch Comp Sci Shanghai Peoples R China Zhejiang Univ Hangzhou Peoples R China Tencent Youtu Lab Shenzhen Peoples R China NAOC CAS Beijing Peoples R China Zhongshan PoolNet Technol Co Ltd Zhongshan Fudan Joint Innovat Ctr Hangzhou Peoples R China

ISBN: (纸本)9798350344868;9798350344851

Classifying an entire Whole Slide image (WSI) in a single forward pass is challenging due to its vast resolution. Consequently, current effort on WSI classification resorts to multiple instance learning (MIL), using patch-wise instances to predict categories under image-wise supervision. However, recent MIL methods usually follow implicit instance selection strategy and ignore the effect from inherent patch category imbalances. In a statistical sense, negative patches dominate in WSIs and provide sufficient samples for accurate density estimation. Therefore, in this paper, we learn from anomaly detection and propose a deep MIL framework which learns a hybrid negative probability model to bootstrap discovery of potential positive lesion. We associate attention-based MIL approach with a regularization loss function to explicitly improve patch selection process in positive images. Experiments conducted on benchmarks of WSI recognition demonstrate that our method brings significant improvement to classic attention-based MIL baseline and achieves state-of-the-art performance.

关键词： multiple instance learning weakly-supervised learning whole slide image

来源：评论

学校读者我要写书评

暂无评论

Computational techniques for parameter estimation of gravitational wave signals

引用

WILEY INTERDISCIPLINARY REVIEWS-COMPUTATIONAL STATISTICS 2022年第1期14卷 e1532-e1532页

作者： Meyer, Renate Edwards, Matthew C. Maturana-Russel, Patricio Christensen, Nelson Univ Auckland Dept Stat Auckland New Zealand Auckland Univ Technol Dept Math Sci Auckland New Zealand Univ Cote Azur Observ Cote Azur Artemis Nice France

Since the very first detection of gravitational waves from the coalescence of two black holes in 2015, Bayesian statistical methods have been routinely applied by LIGO and Virgo to extract the signal out of noisy interferometric measurements, obtain point estimates of the physical parameters responsible for producing the signal, and rigorously quantify their uncertainties. Different computational techniques have been devised depending on the source of the gravitational radiation and the gravitational waveform model used. Prominent sources of gravitational waves are binary black hole or neutron star mergers, the only objects that have been observed by detectors to date. But also gravitational waves from core-collapse supernovae, rapidly rotating neutron stars, and the stochastic gravitational-wave background are in the sensitivity band of the ground-based interferometers and expected to be observable in future observation runs. As nonlinearities of the complex waveforms and the high-dimensional parameter spaces preclude analytic evaluation of the posterior distribution, posterior inference for all these sources relies on computer-intensive simulation techniques such as Markov chain Monte Carlo methods. A review of state-of-the-art Bayesian statistical parameter estimation methods will be given for researchers in this cross-disciplinary area of gravitational wave data analysis. This article is categorized under: Applications of Computational Statistics > Signal and image processing and Coding statistical and Graphical methods of Data Analysis > Markov Chain Monte Carlo (MCMC) statistical Models > Time Series Models

关键词： Bayesian inference Markov chain Monte Carlo Nested Sampling parameter estimation signal processing

来源：评论

学校读者我要写书评

暂无评论

FEDKA: FEDERATED KNOWLEDGE AUGMENTATION FOR MULTI-CENTER MEDICAL image SEGMENTATION ON NON-IID DATA 49

FEDKA: FEDERATED KNOWLEDGE AUGMENTATION FOR MULTI-CENTER MED...

引用

49th IEEE International conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Zhang, Yuhao Duan, Shaoming Zha, Xinyu Su, Jinhang Han, Peiyi Liu, Chuanyi Harbin Inst Technol Shenzhen Sch Comp Sci Shenzhen Peoples R China Peng Cheng Lab Shenzhen Peoples R China Guangdong Prov Key Lab Novel Secur Intelligence T Shenzhen Peoples R China

ISBN: (纸本)9798350344868;9798350344851

Federated learning (FL) allows decentralized medical institutions to collaboratively learn a shared global model without breaching data privacy. However, in the context of medical image segmentation, data distributions across centers may vary a lot due to the diverse imaging protocols, vendors and partial annotation, which usually hampers the optimization convergence and the performance of FL. In this paper, we propose a novel approach called federated knowledge augmentation (FedKA) to address the non-IID (non-independent and identically distributed) problem in medical image segmentation within FL. FedKA first designs a pixel-wise knowledge augmentation method to preserve the knowledge of globally labeled regions for the local model during training, and augments each local feature statistical knowledge based on a mixture of Gaussian distribution. Our experiments on public datasets show the superiority of FedKA over the state-of-the-art methods in test performance.

关键词： Federated learning Knowledge augmentation non-IID data

来源：评论

学校读者我要写书评

暂无评论

Fourier Diffusion for Sparse CT Reconstruction

Fourier Diffusion for Sparse CT Reconstruction

引用

conference on Medical Imaging - Physics of Medical Imaging

作者： Liu, Anqi Gang, Grace J. Stayman, J. Webster Johns Hopkins Univ Biomed Engn Baltimore MD 21218 USA Univ Penn Radiol Philadelphia PA USA

ISBN: (纸本)9781510671553;9781510671546

Sparse CT reconstruction continues to be an area of interest in a number of novel imaging systems. Many different approaches have been tried including model-based methods, compressed sensing approaches, and most recently deep-learning-based processing. Diffusion models, in particular, have become extremely popular due to their ability to effectively encode rich information about images and to allow for posterior sampling to generate many possible outputs. One drawback of diffusion models is that their recurrent structure tends to be computationally expensive. In this work we apply a new Fourier diffusion approach that permits processing with many fewer time steps than the standard scalar diffusion model. We present an extension of the Fourier diffusion technique and evaluate it in a simulated breast cone-beam CT system with a sparse view acquisition.

关键词： Diffusion image processing Modulation transfer functions image restoration stochastic processes Data modeling Computed tomography CT reconstruction Data acquisition Reverse modeling

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：