基于Sobel滤波器的图像风格转换算法

基于迭代的图像风格转换在图像重组时未考虑内容图像的结构,导致生成的图像存在线条扭曲.为约束图像重组时的信息,提出一种基于边缘检测的图像风格转换算法.通过Sobel滤波器在内容图像和生成图像相同的卷积层上提取边缘信息,同时以均方误差作为损失函数.在此基础上,将边缘损失、内容损失和风格损失的加权代数和作为神经网络的总损失.实验结果表明,该算法能够有效抑制图像的线条扭曲,减少图像噪声,生成更高质量的图像.     

基于Sobel滤波器的图像风格转换算法

基于迭代的图像风格转换在图像重组时未考虑内容图像的结构,导致生成的图像存在线条扭曲.为约束图像重组时的信息,提出一种基于边缘检测的图像风格转换算法.通过Sobel滤波器在内容图像和生成图像相同的卷积层上提取边缘信息,同时以均方误差作为损失函数.在此基础上,将边缘损失、内容损失和风格损失的加权代数和作为神经网络的总损失.实验结果表明,该算法能够有效抑制图像的线条扭曲,减少图像噪声,生成更高质量的图像.     

面向三维模型视图特征提取的残差卷积网络优化

在已有残差卷积神经网络基础上,采用加权损失函数提高视图特征的可分性,提出面向三维模型视图特征提取的残差卷积网络优化算法.首先对三维模型进行多视图渲染得到二维视图;然后通过残差网络扩展模块加深网络深度;最后采用中心损失函数和交叉熵损失函数定义加权损失函数,解决交叉熵损失函数因为类内距离小于类间距离而导致的特征不可分问题.在ModelNet数据集上的实验结果表明,该算法提取到的特征在三维模型分类问题上性能表现优异.     

去除磁共振成像图像莱斯噪声的加权扩散

针对各向同性扩散易于造成图像边缘等特征区域的模糊以及相干增强扩散易于在图像背景区域内产生伪条纹的问题,提出了一种根据磁共振成像（MRI）图像莱斯噪声分布特点来对其进行降噪的加权扩散算法。该算法以MRI图像背景区域的莱斯噪声方差作为区分MRI图像背景区域和感兴趣的边缘特征区域二者特征差异的阈值。基于该阈值,该算法构造了一个加权函数,并用该函数对各向同性扩散和相干增强扩散进行加权。加权函数根据图像在不同结构区域的变化,自适应地调整两种扩散的权值,从而充分发挥两种扩散的优势并克服各自的不足。实验结果表明,该算法在峰值信噪比（PSNR）及平均结构相似度（MSSIM）的评价上优于一些经典算法。因此,该算法的降噪及保护、增强边缘的能力更为优越。     

基于加权损失函数的多尺度对抗网络图像语义分割算法

针对现有的语义分割算法存在分割结果空间不一致的问题,提出一种基于加权损失函数的多尺度对抗网络语义分割算法。在DeepLab v3基本框架的基础上,引入Pix2pix网络作为生成对抗网络模型,实现多尺度对抗网络语义分割。同时,为增加模型的泛化能力与训练精度,提出将传统的多分类交叉熵损失函数与生成器输出的内容损失函数和鉴别器输出的对抗损失函数相结合,构建加权损失函数。大量定性定量实验结果表明,该算法能够识别并分割细小的物体,其语义分割性能超过现有的深度网络,在保证语义分割空间一致性的同时提高了分割效率。     

基于多结构元素的数学形态学图像边缘检测

基于改进的单结构元素抗噪型形态边缘检测算子和形态滤波思想,提出了一种多结构元素的多路加权合成形态边缘检测算法。在该算法中,采用峰值信噪比代替固定均值来确定加权参数,是一种自适应方法。与传统的边缘检测算法的对比实验表明,该算法图像边缘检测效果较好,降噪能力也得到了提高。     

一种面向SAR图像的多窗口道路边缘检测算法

道路作为一种重要地物信息,在城市规划等领域中起着不可替代作用。合成孔径雷达（SAR）具有全天候等成像特点,因此基于SAR图像已有许多道路边缘检测算法。提出一种多窗口道路边缘检测算法,来解决相干斑噪声引起的道路边缘误检率高完整性差等问题。该算法首先以加权局部熵的大小为基础,评估SAR图像中像素点落在道路上的概率,然后以该概率为依据,确定每个像素点多窗口融合的权值。最后,对不同大小窗口的边缘检测结果进行加权融合。通过对不同区域的SAR图像切片进行实验,结果表明加权融合后得到的道路边缘的完整性及对噪声的抑制效果均有所提高。     

基于局部边缘特征水平集演化的主动脉CT图像分割

腹腔主动脉所处环境复杂，不可避免的造成弱边缘和边缘不均匀等问题.提出一种基于局部边缘特征的水平集演化算法，根据其所处水平集内部与外部相邻区域的相关性赋值加权因子，使得能量函数最小化.实验结果表明，本算法在实验精度和稳定性方面取得了良好的效果.     

基于加权直觉模糊集合的聚类模型

针对已有基于直觉模糊集的聚类方法的局限性,提出了一种基于加权直觉模糊集合的聚类模型——WIFSCM。在该模型中,提出了特定特征空间下的等价样本和加权直觉模糊集合的概念;并推导出基于等价样本和加权直觉模糊集合的直觉模糊聚类算法的目标函数,利用该目标函数推导出直觉模糊聚类中心迭代算法和隶属度矩阵迭代算法;定义了基于加权直觉模糊集合的密度函数,确定了初始聚类中心,减少了迭代次数。通过灰度图像分割实验,证明了该模型的有效性,同时与普通直觉模糊集FCM聚类算法(IFCM)相比,聚类速度提高近百倍。     

基于加权边缘弱化引导滤波的人脸光照补偿

光照的变化是影响人脸识别结果的重要因素之一,针对这一问题,提出一种基于加权边缘弱化引导滤波的人脸光照补偿方法。首先为引导滤波损失函数添加一个可区分边缘细节的惩罚项,然后为惩罚项加权,加权系数由正面光照样本的类间平均脸计算得到,最后将滤波后的图像作为自商图中的平滑图,得到光照补偿图像。实验结果表明,该方法弱化了人脸平滑区域由光照造成的边缘细节噪声,且使用光照补偿图像作为人脸识别输入,能有效提高人脸识别准确率,特别在光照大范围变化时,识别准确率提升程度更高。     

Regularized margin-based conditional log-likelihood loss for prototype learning

The classification performance of nearest prototype classifiers largely relies on the prototype learning algorithm. The minimum classification error (MCE) method and the soft nearest prototype classifier (SNPC) method are two important algorithms using misclassification loss. This paper proposes a new prototype learning algorithm based on the conditional log-likelihood loss (CLL), which is based on the discriminative model called log-likelihood of margin (LOGM). A regularization term is added to avoid over-fitting in training as well as to maximize the hypothesis margin. The CLL in the LOGM algorithm is a convex function of margin, and so, shows better convergence than the MCE. In addition, we show the effects of distance metric learning with both prototype-dependent weighting and prototype-independent weighting. Our empirical study on the benchmark datasets demonstrates that the LOGM algorithm yields higher classification accuracies than the MCE, generalized learning vector quantization (GLVQ), soft nearest prototype classifier (SNPC) and the robust soft learning vector quantization (RSLVQ), and moreover, the LOGM with prototype-dependent weighting achieves comparable accuracies to the support vector machine (SVM) classifier.     

一种自适应混合权重的自步学习方法

自步学习是一种受人类和动物学习过程启发的学习机制,它赋予训练样本不同的权重,从而逐步将简单到更复杂的样本纳入训练集进行学习.自步学习在目标函数中加入自步正则项控制学习过程.目前存在多种形式的自步权重正则项,不同的正则项可能会导致不同的学习性能.其中,混合权重正则项同时具有硬权重和软权重的特点,因而被广泛应用在众多自步学习问题中.然而,当前的混合权重方法只结合了对数软权重,形式较为单一.此外,相较于软权重或硬权重方式,混合权重方法引入了更多的参数.提出一种自适应混合权重的自步正则方法来克服形式单一和参数难以调节的问题.一方面,在学习的过程中权重的表示形式能够自适应进行调整,另一方面,可以根据样本损失分布特点来自适应混合权重引入的自步参数,从而减少参数对人为经验的依赖.行为识别和多媒体事件检测上的实验结果表明提出的方法可以有效地解决权重形式和参数的自适应问题.     

基于标签噪声鲁棒学习的疾病风险预测

疾病风险预测能够筛查易患人群, 并在早期进行预防干预措施以降低疾病的发生率及死亡率. 随着机器学习技术的快速发展, 基于机器学习的疾病风险预测得到了广泛应用. 然而, 机器学习十分依赖于高质量的标注信息, 医疗数据中存在的标签噪声会给构建高性能的疾病风险预测算法带来严峻挑战. 针对这一问题, 本文提出了一种基于深度神经网络和动态截断损失函数的噪声鲁棒学习方法用于疾病风险预测. 该方法引入动态截断损失函数, 融合了传统交叉熵函数的隐式加权特性和均方差损失函数的标签噪声鲁棒性; 通过构造训练损失下界, 并引入样本动态加权机制减小可疑样本的梯度, 限制可能的带噪样本在训练过程中的权重, 进一步增强模型的鲁棒性. 以脑卒中筛查数据集为例进行实验, 结果表明本文算法在各个标签噪声比例下均能取得良好的预测性能, 可降低疾病风险预测中标签噪声的负面影响, 实现了带有标签噪声数据的鲁棒学习.     

Optimal sensitivity bound estimation and controller design

An explicit computational form is given for the estimation of the smallest upper bound on the sensitivity function over an operating band for a given stability margin in a single right half-plane (RHP) zero scalar system. A stable minimum-phase weighting function is constructed to meet such an infimum and the given stability margin with the H^∞ criterion. A numerical example is presented to demonstrate the optimal sensitivity estimation, weighting function construction and controller design.     

Large Margin Feature Weighting Method via Linear Programming

The problem of feature selection is a difficult combinatorial task in machine learning and of high practical relevance. In this paper, we consider feature selection method for multimodally distributed data, and present a large margin feature weighting method for k-nearest neighbor (kNN) classifiers. The method learns the feature weighting factors by minimizing a cost function, which aims at separating different classes by large local margins and pulling closer together points from the same class, based on using as few features as possible. The consequent optimization problem can be efficiently solved by Linear Programming. Finally, the proposed approach is assessed through a series of experiments with UCI and microarray data sets, as well as a more specific and challenging task, namely, radar high-resolution range profiles (HRRP) automatic target recognition (ATR). The experimental results demonstrate the effectiveness of the proposed algorithms.     

基于标记权重的多标记特征选择算法

在多标记学习中,特征选择是解决多标记数据高维性的有效手段。每个标记对样本的可分性程度不同,这可能会为多标记学习提供一定的信息。基于这一假设,提出了一种基于标记权重的多标记特征选择算法。该算法首先利用样本在整个特征空间的分类间隔对标记进行加权,然后将特征在整个标记集合下对样本的可区分性作为特征权重,以此衡量特征对标记集合的重要性。最后,根据特征权重对特征进行降序排列,从而得到一组新的特征排序。在6个多标记数据集和4个评价指标上的实验结果表明,所提算法优于一些当前流行的多标记特征选择算法。     

基于大间隔方法的汉语组块分析

汉语组块分析是中文信息处理领域中一项重要的子任务.在一种新的结构化SVMs(support vectormachines)模型的基础上,提出一种基于大间隔方法的汉语组块分析方法.首先,针对汉语组块分析问题设计了序列化标注模型;然后根据大间隔思想给出判别式的序列化标注函数的优化目标,并应用割平面算法实现对特征参数的近似优化训练.针对组块识别问题设计了一种改进的F1 损失函数,使得F1损失值能够依据每个句子的实际长度进行相应的调整,从而能够引入更有效的约束不等式.通过在滨州中文树库CTB4 数据集上的实验数据显示,基于改进的F1 损失函数所产生的识别结果优于Hamming 损失函数,各种类型组块识别的总的F1 值为91.61%,优于CRFs(conditional random fields)和SVMs 方法.     

Large-margin nearest neighbor classifiers via sample weight learning

The nearest neighbor classification is a simple and yet effective technique for pattern recognition. Performance of this technique depends significantly on the distance function used to compute similarity between examples. Some techniques were developed to learn weights of features for changing the distance structure of samples in nearest neighbor classification. In this paper, we propose an approach to learning sample weights for enlarging margin by using a gradient descent algorithm to minimize margin based classification loss. Experimental analysis shows that the distances trained in this way reduce the loss of the margin and enlarge the hypothesis margin on several datasets. Moreover, the proposed approach consistently outperforms nearest neighbor classification and some other state-of-the-art methods.     

A closed-form reduction of multi-class cost-sensitive learning to weighted multi-class learning

In cost-sensitive learning, misclassification costs can vary for different classes. This paper investigates an approach reducing a multi-class cost-sensitive learning to a standard classification task based on the data space expansion technique developed by Abe et al., which coincides with Elkan's reduction with respect to binary classification tasks. Using this proposed reduction approach, a cost-sensitive learning problem can be solved by considering a standard 0/1 loss classification problem on a new distribution determined by the cost matrix. We also propose a new weighting mechanism to solve the reduced standard classification problem, based on a theorem stating that the empirical loss on independently identically distributed samples from the new distribution is essentially the same as the loss on the expanded weighted training set. Experimental results on several synthetic and benchmark datasets show that our weighting approach is more effective than existing representative approaches for cost-sensitive learning.     

Maximum margin multiple-instance feature weighting

Feature weighting is of considerable importance in machine learning due to its effectiveness to highlight relevant components and suppress irrelevant ones. In this paper, we focus on the feature weighting problem in a specific machine learning area: multiple-instance learning, and propose maximum margin multiple-instance feature weighting (M3IFW) to seek large classification margins in the weighted feature space. The designed M3IFW algorithm can be applied to both standard binary-class multiple-instance learning and the corresponding multi-class learning, and we abbreviate them to B-M3IFW (binary-class M3IFW) and M-M3IFW (multi-class M3IFW), respectively. Both B-M3IFW and M-M3IFW contain three kinds of unknown variables, i.e., positive prototypes, classification margins, and weighting coefficients. We utilize the coordinate ascent algorithm to update the three kinds of unknown variables, respectively and iteratively, and then perform classifications in the weighted feature space. Experiments conducted on synthetic and real-world datasets empirically demonstrate the effectiveness of M3IFW in improving classification accuracies.