In coherent imaging systems, speckle is a signal-dependent noise that visually strongly degrades images' appearance. A huge amount of SAR data has been acquired from different sensors with different wavelengths, resolutions, incidences and polarizations. We extend the nonlocal filtering strategy to the temporal domain and propose a patch-based adaptive temporal filter (PATF) to take advantage of well-registered multi-temporal SAR images. A patch-based generalised likelihood ratio test is processed to suppress the changed object effects on the multitemporal denoising results. Then, the similarities are transformed into corresponding weights with an exponential function. The denoised value is calculated with a temporal weighted average. Spatial adaptive denoising methods can improve the patch-based weighted temporal average image when the time series is limited. The spatial adaptive denoising step is optional when the time series is large enough. Without reference image, we propose using a patch-based auto-covariance residual evaluation method to examine the ratio image between the noisy and denoised images and look for possible remaining structural contents. It can process automatically and does not rely on a supervised selection of homogeneous regions. It also provides a global score for the whole image. Numerous results demonstrate the effectiveness of the proposed time series denoising method and the usefulness of the residual evaluation method.
Detecting Patch Adversarial Attacks with Image Residuals
Department of Electrical and Computer Engineering University of Texas at Austin(德克萨斯大学奥斯汀分校电气与计算机工程系);University of Texas at Austin(德克萨斯大学奥斯汀分校);Department of Electrical and Computer Engineering(电气与计算机工程系)
PAIQ: Patch-Aligned Semantic Injection via Residual Rotation
Tsinghua University(清华大学);Beijing University of Posts and Telecommunications(北京邮电大学);National University of Singapore(新加坡国立大学);Nanyang Technological University(南洋理工大学)
Stochastic-based Patch Filtering for Few-Shot Learning
AIBA, Departament de Matemàtiques & Informàtica Universitat de Barcelona(AIBA,数学与信息学院巴塞罗那大学);Departamento de Ingeniería de Sistemas y Computación Universidad Católica del Norte(系统与计算工程系天主教北方大学);Institute of Neuroscience, Universitat de Barcelona(神经科学研究所巴塞罗那大学)
Deep Spatiotemporal Clutter Filtering of Transthoracic Echocardiographic Images: Leveraging Contextual Attention and Residual Learning
Cardiovascular Imaging and Dynamics, Department of Cardiovascular Sciences, KU Leuven(心血管影像与动力学,心血管科学系,KU莱顿大学);Life and Health Sciences Research Institute (ICVS), School of Medicine, University of Minho(生命与健康科学研究所(ICVS),医学院,蒙德兹大学);Ai–School of Technology, IPCA(2Ai技术学院,IPCA);Department of Cardiac Technology, College of Applied Medical Sciences, Imam Abdulrahman Bin Faisal University(心脏技术系,应用医学科学学院,伊玛目阿卜杜勒拉赫曼·本·法伊兹大学)
A Dilated Residual Hierarchically Fashioned Segmentation Framework for Extracting Gleason Tissues and Grading Prostate Cancer from Whole Slide Images
Khalifa University(哈利法大学);Beihang University(北京航空航天大学);University of Louisville(路易斯维尔大学)
前列腺癌(PCa)是男性中第二致命的癌症形式,并且可以通过检查Gleason组织的结构表示来进行临床分级。本文提出了\RV{a new method}分割格里森组织\RV{(patch-wise) in order to grade PCa from the whole slide images (WSI).}此外,所提出的方法包括两个主要贡献:1)一个协同的混合膨胀因子和层次分解的潜在空间表示有效格里森组织提取,和2)一个三层的损失函数,可以惩罚不同的语义分割模型,准确地提取高度相关的模式。除此之外,在包含10,516个完整载玻片扫描(约71.7M块)的大规模PCa数据集上对所提出的框架进行了广泛评估,其中它在提取Gleason组织方面优于最先进的方案3.22%(就平均交叉-联合而言),在PCa进展分级方面优于最先进的方案6.91%(就F1评分而言)。
Breast Cancer Molecular Subtypes Prediction on Pathological Images with Discriminative Patch Selecting and Multi-Instance Learning
Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所);Xiangya Hospital, Central South University(中南大学湘雅医院);University of Chinese Academy of Sciences(中国科学院大学);Central South University(中南大学)
Patch-based Non-Local Bayesian Networks for Blind Confocal Microscopy Denoising
Simon Fraser University(西蒙弗雷泽大学)
共聚焦显微镜对于组织病理学细胞可视化和量化至关重要。尽管其在生物学中的重要作用,荧光共聚焦显微镜遭受的固有噪声的存在下,在图像采集。非局部块式贝叶斯均值滤波(NLB)直到最近才成为最先进的去噪方法。然而,近年来,经典的去噪方法已经被神经网络超越。在这项工作中,我们建议在贝叶斯深度学习的框架中利用NLB的优势。我们通过设计一个卷积神经网络并训练它来学习高斯模型的参数,该模型近似于无噪声补丁上的先验,给出了它们最近的、相似的但非局部的邻居。然后,我们应用贝叶斯推理,利用先验知识和信息的噪声补丁的过程中近似的无噪声补丁。具体来说,我们使用封闭形式的解析\textit{maximum a posteriori}(MAP)估计的NLB算法,以获得最大化后验分布的无噪声补丁。我们所提出的方法的性能进行评估,共焦显微镜图像与真实噪声泊松-高斯噪声。我们的实验揭示了我们的方法对最先进的无监督去噪技术的优越性。
Non-Local Patch Regression: Robust Image Denoising in Patch Space
Princeton University(普林斯顿大学)
最近在[Chaudhury et al.,Non-Local Euclidean Medians,2012],非局部均值(NLM)的去噪性能可以在大噪声水平下通过用鲁棒的欧几里德中值替换均值来提高。对合成图像和自然图像的数值实验表明,在一定的噪声水平之外,后者的性能始终优于NLM,并且对于具有尖锐边缘的图像来说,效果显著。欧氏均值和中值可以放在一个共同的回归框架中(在斑块空间上),其中欧氏均值考虑残差的l_2范数,而中值考虑残差的l_1范数。那么自然的问题是,如果我们考虑l_p(0<p<1)回归会发生什么?我们在本文中探讨这种可能性。
ProCon: Projection-Consistency Memory for Training-Free Anomaly Detection
Tsinghua University Shenzhen International Graduate School(清华大学深圳国际研究生院);Ratel Soft;Affiliated Fifth Hospital, Wenzhou Medical University(温州医科大学附属第五医院);Chinese Medicine Guangdong Laboratory(广东中医药大学实验室)
Adaptive Safety Filtering for Frozen ACC Policies via Conformal Residual Calibration
Tsinghua Shenzhen International Graduate School, Tsinghua University(清华大学深圳国际研究生院);Wuhan University of Technology(武汉理工大学);Shanghai Jiao Tong University(上海交通大学)
Wenzhou University(温州大学);Memorial University of Newfoundland(纽芬兰纪念大学);Zhejiang University(浙江大学);University of Bath(巴斯大学);University of Guelph(圭尔夫大学);Nanjing University(南京大学)
Tianjin University(天津大学);Xi’an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences(中国科学院西安光学精密机械研究所)
常规卷积神经网络(CNN)使用线性或非线性滤波器来从空间大小为$ H\times W $(通常,$ H $较小且等于$ W$,例如,$ H $是5或7)。通常,滤波器的大小等于输入补丁的大小$ H\times W $。我们认为,等规模策略的代表能力不够强。为了克服这个缺点,我们建议使用子补丁滤波器的空间尺寸$ h\times w $小于$ H\times W $。建议的子补丁滤波器由两个后续的过滤器。第一个是空间大小为$ h\times w $的线性滤波器,其目的是从空间域提取特征。第二个是空间大小为$ 1\times 1 $的,用于加强不同输入特征通道之间的连接,并用于减少参数的数量。子面片滤波器与输入面片卷积,得到的网络称为子面片网络。以一个子网络的输出作为输入,我们进一步重复构造子网络,直到输出在空间域中只包含一个神经元。这些子补丁网络形成一个新的网络称为级联子补丁网络(CSNet)。CSNet生成的要素图层称为csconv图层。对于整个输入图像,我们通过堆叠一系列csconv层来构建深度神经网络。在四个基准数据集上的实验结果证明了所提出的CSNet的有效性和紧凑性。例如,我们的CSNet在CIFAR10数据集上达到了$ 5.68\% $的测试误差,而没有模型平均。据我们所知,这是CIFAR10数据集上获得的最佳结果。
Continuous Patch Stitching for Block-wise Image Compression
School of Electronic and Information Engineering, Beihang University(北京航空航天大学电子信息工程学院);School of Electronic and Information Engineering, University of Electronic Science and Technology of China(电子科技大学电子信息工程学院)
Center for Computational Mathematics(计算数学中心);University of Colorado at Denver and Health Sciences Center(科罗拉多大学丹佛健康科学中心);National Center for Atmospheric Research(美国国家大气研究中心)