检索结果-内蒙古大学图书馆

Hyperspectral image Classification With Markov Random Fields and a Convolutional neural Network

IEEE TRANSACTIONS ON image processing 2018年第5期27卷 2354-2367页

作者： Cao, Xiangyong Zhou, Feng Xu, Lin Meng, Deyu Xu, Zongben Paisley, John Xi An Jiao Tong Univ Sch Math & Stat Xian 710049 Shaanxi Peoples R China Xidian Univ Natl Lab Radar Signal Proc Xian 710071 Shaanxi Peoples R China NYU Multimedia & Visual Comp Lab Abu Dhabi 129188 U Arab Emirates Columbia Univ Dept Elect Engn New York NY 10027 USA Columbia Univ Data Sci Inst New York NY 10027 USA

This paper presents a new supervised classification algorithm for remotely sensed hyperspectral image (HSI) which integrates spectral and spatial information in a unified Bayesian framework. First, we formulate the HSI classification problem from a Bayesian perspective. Then, we adopt a convolutional neural network (CNN) to learn the posterior class distributions using a patch-wise training strategy to better use the spatial information. Next, spatial information is further considered by placing a spatial smoothness prior on the labels. Finally, we iteratively update the CNN parameters using stochastic gradient decent and update the class labels of all pixel vectors using alpha-expansion min-cut-based algorithm. Compared with the other state-of-the-art methods, the classification method achieves better performance on one synthetic data set and two benchmark HSI data sets in a number of experimental settings.

关键词： Hyperspectral image classification Markov random fields convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Hyperparameter Optimization in Black-box image processing using Differentiable Proxies

引用

ACM TRANSACTIONS ON GRAPHICS 2019年第4期38卷 27-27页

作者： Tseng, Ethan Yu, Felix Yang, Yuting Mannan, Fahim St Arnaud, Karl Nowrouzezahrai, Derek Lalonde, Jean-Francois Heide, Felix Princeton Univ Princeton NJ 08544 USA Algolux Montreal PQ Canada McGill Univ Montreal PQ Canada Univ Laval Quebec City PQ Canada

Nearly every commodity imaging system we directly interact with, or indirectly rely on, leverages power efficient, application-adjustable black-box hardware image signal processing (ISPs) units, running either in dedicated hardware blocks, or as proprietary software modules on programmable hardware. The configuration parameters of these black-box ISPs often have complex interactions with the output image, and must be adjusted prior to deployment according to application-specific quality and performance metrics. Today, this search is commonly performed manually by "golden eye" experts or algorithm developers leveraging domain expertise. We present a fully automatic system to optimize the parameters of black-box hardware and software image processing pipelines according to any arbitrary (i.e., application-specific) metric. We leverage a differentiable mapping between the configuration space and evaluation metrics, parameterized by a convolutional neural network that we train in an end-to-end fashion with imaging hardware in-the-loop. Unlike prior art, our differentiable proxies allow for high-dimension parameter search with stochastic first-order optimizers, without explicitly modeling any lower-level image processing transformations. As such, we can efficiently optimize black-box image processing pipelines for a variety of imaging applications, reducing application-specific configuration times from months to hours. Our optimization method is fully automatic, even with black-box hardware in the loop. We validate our method on experimental data for real-time display applications, object detection, and extreme low-light imaging. The proposed approach outperforms manual search qualitatively and quantitatively for all domain-specific applications tested. When applied to traditional denoisers, we demonstrate that-just by changing hyperparameters-traditional algorithms can outperform recent deep learning methods by a substantial margin on recent benchmarks.

关键词： image processing

来源：评论

学校读者我要写书评

暂无评论

Exposing computer generated images by using deep convolutional neural networks

引用

signal processing-image COMMUNICATION 2018年 66卷 113-126页

作者： de Rezende, Edmar R. S. Ruppert, Guilherme C. S. Theophilo, Antonio Tokuda, Eric K. Carvalho, Tiago CTI Renato Archer BR-13069901 Campinas SP Brazil Fed Inst Sao Paulo BR-13069901 Campinas SP Brazil Univ Sao Paulo BR-05008090 Sao Paulo SP Brazil

The recent computer graphics developments have upraised the quality of the generated digital content, astonishing the most skeptical viewer. Games and movies have taken advantage of this fact but, at the same time, these advances have brought serious negative impacts like the ones yielded by fake images produced with malicious intents. Digital artists can compose artificial images capable of deceiving the great majority of people, turning this into a very dangerous weapon in a timespan currently know as "Fake News/Post-Truth" Era. In this work, we propose a new approach for dealing with the problem of detecting computer generated images, through the application of deep convolutional networks and transfer learning techniques. We start from Residual Networks and develop different models adapted to the binary problem of identifying if an image was, or not, computer generated. Differently from the current state-of-the-art approaches, we do not rely on hand-crafted features, but provide to the model the raw pixel information, achieving the same 0.97 performance of state-of-the-art methods with three main advantages: (i) executes considerably faster than state-of-the-art methods with equivalent accuracy;(ii) eliminates the laborious and manual step of specialized features extraction and selection, and (iii) is very robust against image processing operations as noise addition, blur and JPEG compression.

关键词： Digital forensics CG detection Deep learning Transfer learning Fake news

来源：评论

学校读者我要写书评

暂无评论

Uses of Complex Wavelets in Deep Convolutional neural Networks

Uses of Complex Wavelets in Deep Convolutional Neural Networ...

引用

作者： Cotter,Fergal Cambridge University

image understanding has long been a goal for computer vision. It has proved to be an exceptionally difficult task due to the large amounts of variability that are inherent to objects in a scene. Recent advances in supervised learning methods, particularly convolutional neural networks (CNNs), have pushed forth the frontier of what we have been able to train computers to do. Despite their successes, the mechanics of how these networks are able to recognize objects are little understood, and the networks themselves are often very difficult and time-consuming to train. It is very important that we improve our current approaches in every way possible. A CNN is built from connecting many learned convolutional layers in series. These convolutional layers are fairly crude in terms of signal processing - they are arbitrary taps of a finite impulse response filter, learned through stochastic gradient descent from random initial conditions. We believe that if we reformulate the problem, we may achieve many insights and benefits in training CNNs. Noting that modern CNNs are mostly viewed from and analyzed in the spatial domain, this thesis aims to view the convolutional layers in the frequency domain (viewing things in the frequency domain has proved useful in the past for denoising, filter design, compression and many other tasks). In particular, we use complex wavelets (rather than the Fourier transform or the discrete wavelet transform) as basis functions to reformulate image understanding with deep networks. In this thesis, we explore the most popular and well-developed form of using complex wavelets in deep learning, the ScatterNet from Stephane Mallat. We explore its current limitations by building a DeScatterNet and found that while it has many nice properties, it may not be sensitive to the most appropriate shapes for understanding natural images. We then develop a locally invariant convolutional layer, a combination of a complex wavelet transform, a modulus operation,

关键词：

来源：评论

学校读者我要写书评

暂无评论

Improved Protein Residue-Residue Contact Prediction Using image Denoising methods 26

Improved Protein Residue-Residue Contact Prediction Using Im...

引用

European signal processing Conference (EUSIPCO)

作者： Villegas-Morcillo, Amelia Morales-Cordovilla, Juan A. Gomez, Angel M. Sanchez, Victoria Univ Granada Dept Signal Theory Telemat & Commun Granada Spain

ISBN: (纸本)9789082797015

A protein contact map is a simplified matrix representation of the protein structure, where the spatial proximity of two amino acid residues is reflected. Although the accurate prediction of protein inter-residue contacts from the amino acid sequence is an open problem, considerable progress has been made in recent years. This progress has been driven by the development of contact predictors that identify the co-evolutionary events occurring in a protein multiple sequence alignment (MSA). However, it has been shown that these methods introduce Gaussian noise in the estimated contact map, making its reduction necessary. In this paper, we propose the use of two different Gaussian denoising approximations in order to enhance the protein contact estimation. These approaches are based on (i) sparse representations over learned dictionaries, and (ii) deep residual convolutional neural networks. The results highlight that the residual learning strategy allows a better reconstruction of the contact map, thus improving contact predictions.

关键词： Protein Contact Map Evolutionary Coupling image Denoising Sparse Representations Dictionary Learning Deep Convolutional neural Networks Residual Learning

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Utilization in Beamforming Enhancement for Medical Ultrasound

Deep Learning Utilization in Beamforming Enhancement for Med...

引用

IEEE Annual International Computer Software and Applications Conference (COMPSAC)

作者： Mariam Fouad Yousef Metwally Georg Schmitz Michael Huebner Mohamed A. Abd El Ghany Ruhr University Bochym (RUB) Germany and German University in Cairo (GUC) Egypt German University in Cairo (GUC) Egypt Ruhr University Bochum (RUB) Germany BTU Cottbus - Senftenberg Germany German University in Cairo (GUC) Egypt and TU Darmstadt (TUD) Germany

ISBN: (数字)9781728173030

ISBN: (纸本)9781728173047

Ultrasound imaging offers a low cost, noninvasive and portable system, which allowed it to be an invaluable tool for medical imaging. However, the quality of the reconstructed images depends significantly on the beamforming technique utilized. Although advanced data-adaptive methods of reconstruction such as Minimum Variance (MV) beamforming can recover image quality much higher than conventional techniques, their implementation also entails a heavy computational burden. This dichotomy hinders the ultrasound imaging use as a standalone device in some applications such as early breast cancer detection. Deep neural networks (DNNs) have shown a huge potential when applied to many Artificial intelligence (AI) research fields. In this work, the use of Deep learning in improving the quality of the beamforming technique Delay and Sum (DAS) normally used for ultrasound (US) images reconstruction is explored. Three different architectures are implemented: Convolutional AutoEncoder (CAE), Fully Connected network (FC) and U-Net-like architecture. They were trained on datasets simulated using field ii. The dataset consists of input-output pairs where the input is Noisy DAS beamformed scan lines and the output is MV beamformed non-noisy scan lines. The networks show a great ability in predicting the beamformed signals along with significantly reducing noise in the reconstructed images. Additionally, the proposed networks improve other image characteristics such as scatterer size and position along with reducing tail characteristic normally found in DAS beamformed ultrasound images. US images constructed by the networks achieved better quality metrics that surpass conventional DAS beamformed images. The CAE, U-net-like architecture, and FC enhanced the signal to noise ratio (SNR) compared to DAS by 218%, 165% and 136% respectively. Additionally, the networks showed higher Contrast to Noise Ratio (CNR) and Contrast Ratio (CR) metrics than DAS beamformed signals. Finally, the propo

关键词： Array signal processing Ultrasonic imaging image reconstruction Delays Imaging Computer architecture Covariance matrices

来源：评论

学校读者我要写书评

暂无评论

Deep Learning for Passive Synthetic Aperture Radar

引用

IEEE JOURNAL OF SELECTED TOPICS IN signal processing 2018年第1期12卷 90-103页

作者： Yonel, Bariscan Mason, Eric Yazici, Birsen Rensselaer Polytech Inst Dept Elect Comp & Syst Engn Troy NY 12180 USA

We introduce a deep learning (DL) framework for inverse problems in imaging, and demonstrate the advantages and applicability of this approach in passive synthetic aperture radar (SAR) image reconstruction. We interpret image reconstruction as a machine learning task and utilize deep networks as forward and inverse solvers for imaging. Specifically, we design a recurrent neural network (RNN) architecture as an inverse solver based on the iterations of proximal gradient descent optimization methods. We further adapt the RNN architecture to image reconstruction problems by transforming the network into a recurrent auto-encoder, thereby allowing for unsupervised training. Our DL based inverse solver is particularly suitable for a class of image formation problems in which the forward model is only partially known. The ability to learn forward models and hyper parameters combined with unsupervised training approach establish our recurrent auto-encoder suitable for real world applications. We demonstrate the performance of our method in passive SAR image reconstruction. In this regime a source of opportunity, with unknown location and transmitted waveform, is used to illuminate a scene of interest. We investigate recurrent auto-encoder architecture based on the l(1 )and l(0) constrained least-squares problem. We present a projected stochastic gradient descent based training scheme which incorporates constraints of the unknown model parameters. We demonstrate through extensive numerical simulations that our DL based approach out performs conventional sparse coding methods in terms of computation and reconstructed image quality, specifically, when no information about the transmitter is available.

关键词： Deep learning image reconstruction passive imaging synthetic aperture radar passive radar

来源：评论

学校读者我要写书评

暂无评论

A Comparative study of Global and Deep Features for the analysis of user-generated natural disaster related images 13

A Comparative study of Global and Deep Features for the anal...

引用

13th IEEE image, Video, and Multidimensional signal processing Workshop (IVMSP)

作者： Ahmad, Kashif Sohail, Amir Conci, Nicola De Natale, Francesco Univ Trento Trento Italy

ISBN: (纸本)9781538609514

The paper addresses the problem of adverse events (natural disasters) recognition in user-generated images from social media, addressing the problem from two complementary perspectives. On one side, we aim to provide a comprehensive comparative analysis of different feature extraction and classification algorithms, relying on two different families of feature extraction algorithms, namely (i) Global features and (ii) Deep features. On the other hand, we demonstrate that the fusion of different feature extraction and classification strategies can outperform the single methods by jointly exploiting the capabilities of individual feature descriptors. The evaluation of the methods are carried out on two datasets, including a benchmark and a self-collected dataset.

关键词： Natural Disasters Multimedia Analysis Global Features Deep neural Networks Retrieval

来源：评论

学校读者我要写书评

暂无评论

Analysis of Adversarial Attacks against CNN-based image Forgery Detectors 26

Analysis of Adversarial Attacks against CNN-based Image Forg...

引用

26th European signal processing Conference (EUSIPCO)

作者： Gragnaniello, Diego Marra, Francesco Poggi, Giovanni Verdoliva, Luisa Univ Federico II Naples Dept Elect Engn & Informat Technol Naples Italy

ISBN: (纸本)9789082797015

With the ubiquitous diffusion of social networks, images are becoming a dominant and powerful communication channel. Not surprisingly, they are also increasingly subject to manipulations aimed at distorting information and spreading fake news. In recent years, the scientific community has devoted major efforts to contrast this menace, and many image forgery detectors have been proposed. Currently, due to the success of deep learning in many multimedia processing tasks, there is high interest towards CNN-based detectors, and early results are already very promising. Recent studies in computer vision, however, have shown CNNs to be highly vulnerable to adversarial attacks, small perturbations of the input data which drive the network towards erroneous classification. In this paper we analyze the vulnerability of CNN-based image forensics methods to adversarial attacks, considering several detectors and several types of attack, and testing performance on a wide range of common manipulations, both easily and hardly detectable.

关键词： image counterforensics convolutional neural networks generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Soft Dropout And Its Variational Bayes Approximation

Soft Dropout And Its Variational Bayes Approximation

引用

IEEE Workshop on Machine Learning for signal processing

作者： Jiyang Xie Zhanyu Ma Guoqiang Zhang Jing-Hao Xue Zheng-Hua Tan Jun Guo Pattern Recognition and Intelligent Systems Lab Beijing University of Posts and Telecommunications China School of Electrical and Data Engineering University of Technology Sydney Australia Department of Statistical Science University College London United Kingdom Department of Electronic Systems Aalborg University Denmark

Soft dropout, a generalization of standard “hard” dropout, is introduced to regularize the parameters in neural networks and prevent overfitting. We replace the “hard” dropout mask following a Bernoulli distribution with the “soft” mask following a beta distribution to drop the hidden nodes in different levels. The soft dropout method can introduce continuous mask coefficients in the interval of [0, 1], rather than only zero and one. Meanwhile, in order to implement the adaptive dropout rate via adaptive distribution parameters, we respectively utilize the half-Gaussian distributed and the half-Laplace distributed variables to approximate the beta distributed masks and apply a variation of variational Bayes optimization called stochastic gradient variational Bayes (SGVB) algorithm to optimize the distribution parameters. In the experiments, compared with the standard soft dropout with fixed dropout rate, the adaptive soft dropout method generally improves the performance. In addition, the proposed soft dropout and its adaptive versions achieve performance improvement compared with the referred methods on both image classification and regression tasks.

关键词： neural networks Probability density function Standards Training Bayes methods Approximation algorithms Optimization

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：