低秩先验引导的无监督域自适应行人重识别

无监督域自适应行人重识别在智能监控中发挥着重要作用,并引起了研究者的广泛关注.尽管目前的研究已经取得了较大进步,但不同数据集之间的域偏移问题给行人重识别带来极大挑战.研究发现,在连续时间里,同一摄像机视角下的行人图像具有相同的风格,如果将这种风格信息从行人图像中分离出去,将有效缓解由图像风格差异引起的域偏移问题.为此,提出一种低秩先验引导的域不变信息分离的字典学习方案.根据风格信息的低秩先验性,将行人图像特征中的风格信息和行人身份信息分离开来,根据同一身份行人属性的域不变性建立视觉特征与属性之间的联系,缓解域偏移所带来的影响,通过自训练策略来调整学习参数.实验表明,方法的性能在很多数据集上超过了传统的无监督域自适应行人重识别方法以及部分基于深度学习的无监督域自适应行人重识别方法.     

基于学习体型表征的行人再识别

行人再识别是计算机视觉领域的一项重要任务,但大多数现有模型很大程度上依赖于颜色外观。针对目前很少研究解决目标人物衣服不一致的行人再识别问题,提出一种新的表征学习模型。该模型通过对抗性学习和特征分离来产生不受服装颜色或图案影响的体型特征表示。同时,由于缺乏包含同一个人服装变化的行人再识别数据集,创建了一个合成数据集来模拟服装变化。4个数据集(两个基准行人再识别数据集,一个跨模态行人再识别数据集,合成数据集)的定量和定性结果证实了该方法对几种最先进的方法的鲁棒性和优越性。     

Unsupervised person re-identification based on removal of camera bias and dynamic updating of the memory bank

In recent years, unsupervised person reidentification technology has made great strides. The technology retrieves images of interested persons under different cameras from massive repositories of unlabeled images. However, in the current research, there are some existing problems, such as the influence of pedestrians appearing across cameras and pseudo-label noise. To solve these problems, we conduct research in two ways: removing the camera bias and dynamically updating the memory model. In removing the camera bias, based on a learnable channel attention module, the features that are only related to cameras can be extracted from the feature map, thereby removing the camera bias in the global features and obtaining the features that can represent the pedestrians. In regards to dynamically updating the memory model, since the instance features do not necessarily belong to the identity represented by the pseudo-label, we adopt a method to update the memory dynamically according to the distance between the instance features and the category features so that the category features tend to be true. We combine the removal of the camera bias and the dynamic updating of the memory model to better solve problems in this field. Extensive experimentation demonstrates the superiority of our method over the state-of-the-art approaches on fully unsupervised Re-ID tasks.     

基于姿态估计和Transformer模型的遮挡行人重识别

行人重识别是利用人工智能解决边防检查、人员追踪等公共安全应用问题的技术,具有从跨设备采集的图像中识别某一特定行人的能力。但是在人员追踪等问题中,往往会出现行人刻意遮挡、复杂场景环境遮挡等因素,大大提高了行人重识别的难度。针对行人重识别遮挡问题,基于ResNet50网络,结合姿态估计（Pose estimation）和转换器（Transformer）模型,提出了一种改进的行人重识别网络PT-Net,以提高遮挡条件下的行人重识别能力。该方法首先利用现有的姿态估计方法对输入图像进行关键点检测,并将关键点信息与行人特征图像结合起来生成一个基于姿态的行人特征表示;然后利用Transformer模型对基于姿态的行人特征表示编码,用来实现特征对齐和特征融合。论文基于国际公开的数据集Occluded-Duke开展实验验证,结果表明,PT-Net方法相对于基线模型,其均值精度mAP和相似度排序Rank-1指标分别提高了1.3和1.5个百分点,验证了该方法的有效性和优越性。     

Robust Unsupervised Discriminative Dependency Parsing

Discriminative approaches have shown their effectiveness in unsupervised dependency parsing.However,due to their strong representational power,discriminative approaches tend to quickly converge to poor local optima during unsupervised training.In this paper,we tackle this problem by drawing inspiration from robust deep learning techniques.Specifically,we propose robust unsupervised discriminative dependency parsing,a framework that integrates the concepts of denoising autoencoders and conditional random field autoencoders.Within this framework,we propose two types of sentence corruption mechanisms as well as a posterior regularization method for robust training.We tested our methods on eight languages and the results show that our methods lead to significant improvements over previous work.     

不同分辨率图像的角点匹配方法

针对不同分辨率图像的匹配问题,提出了一种利用高斯金字塔的一对多角点匹配方法.采用一种变形的特征描述算子(SIFT)对角点附近的图像区域进行特征提取,根据提取出的特征向量进行角点匹配,并提出一种简单有效的抽样一致性算法以剔除错误匹配点对,最后在一对多角点的匹配结果中选出最佳的匹配作为最终的角点匹配结果.实验结果表明,该算法能有效地克服分辨率的差异给匹配带来的困难,算法简单,可靠性好.     

基于深度小波自动编码器和极限学习机的轴承故障诊断

针对原始振动数据无监督特征学习问题,提出了一种深度小波自动编码器(deep wavelet automatic encoder,DWAE)与鲁棒极限学习机(extreme learning machine,ELM)相结合的滚动轴承的智能故障诊断方法。首先,利用小波函数作为非线性激活函数设计小波自动编码器从而有效地捕获信号特征。其次,利用多个小波自动编码器构造一个深度小波自动编码器来增强无监督特征学习能力。最后,采用鲁棒极限学习机作为分类器,对不同的轴承故障进行分类识别。用该方法对实验所得的轴承振动信号进行对比分析,结果验证了该方法能够在原始振动数据无监督特征学习的条件下该方法优于传统方法和标准深度学习方法。     

Self-supervised human semantic parsing for video-based person re-identification

Video-based person re-identification is an important research topic in computer vision that entails associating a pedestrian’s identity with non-overlapping cameras. It suffers from severe temporal appearance misalignment and visual ambiguity problems. We propose a novel self-supervised human semantic parsing approach (SS-HSP) for video-based person re-identification in this work. It employs self-supervised learning to adaptively segment the human body at pixel-level by estimating motion information of each body part between consecutive frames and explores complementary temporal relations for pursuing reinforced appearance and motion representations. Specifically, a semantic segmentation network within SS-HSP is designed, which exploits self-supervised learning by constructing a pretext task of predicting future frames. The network learns precise human semantic parsing together with the motion field of each body part between consecutive frames, which permits the reconstruction of future frames with the aid of several customized loss functions. Local aligned features of body parts are obtained according to the estimated human parsing. Moreover, an aggregation network is proposed to explore the correlation information across video frames for refining the appearance and motion representations. Extensive experiments on two video datasets have demonstrated the effectiveness of the proposed approach.     

Robust Segmentation Method for Noisy Images Based on an Unsupervised Denosing Filter

Level-set-based image segmentation has been widely used in unsupervised segmentation tasks.Researchers have recently alleviated the influence of image noise on segmentation results by introducing global or local statistics into existing models. Most existing methods are based on the assumption that the distribution of image noise is known or observable. However, real-time images do not meet this assumption. To bridge this gap, we propose a novel level-set-based segmentation method with an unsupervised denoising mechanism. First,a denoising filter is acquired under the unsupervised learning paradigm. Second, the denoising filter is integrated into the level-set framework to separate noise from the noisy image input. Finally, the level-set energy function is minimized to acquire segmentation contours. Extensive experiments demonstrate the robustness and effectiveness of the proposed method when applied to noisy images.     

应用空间约束和二次相似度学习算法的行人再识别

针对空间分布的全局外观潜在变化的行人再识别问题,提出一种基于空间约束和二次相似度学习算法.通过二次相似度函数(QSF)估计每个子区域的相似度,从而形成多项式特征图,并将所有特征图融合到统一的框架中.该框架利用局部相似度和全局相似度的互补优势,结合多个视觉线索进一步提高算法的鲁棒性.实验对比3个公共数据集,结果表明:基于空间约束和二次相似度学习算法具有显著的识别性能.     

基于语义分割注意力与可见区域预测的行人检测方法

为改善图像中遮挡和小尺寸行人的检测精度，提出一种基于语义分割注意力和可见区域预测的行人检测方法.具体地，在SSD(single shot multi-box detector)目标检测网络的基础上，首先优化SSD的超参数设置，使其更适于行人检测;然后在主干网络中引入基于语义分割的注意力分支来增强行人检测特征的表达能力;最后提出一种检测预测模块，它不仅能同时预测行人整体和可见区域，还能利用可见区域预测分支所学的特征去引导整体检测特征的学习，提升检测效果.在Caltech行人检测数据集上进行了实验，所提方法的对数平均缺失率为5.5%，与已有方法相比具有一定的优势.     

基于注意力机制与多尺度特征融合的行人重识别方法

针对行人重识别中因遮挡、姿态变化使模型特征无法充分表达行人信息的问题,提出了基于注意力机制与多尺度特征融合的行人重识别方法.首先使用改进的骨干网络R-ResNet50提取图像特征;其次,抽取网络不同尺度的特征层嵌入注意力机制DANet,使模型更关注于重点信息;最后,对提取出的关键特征进行多尺度特征融合,实现特征间的优势...     

基于关系挖掘的跨模态行人重识别

基于文本的行人重识别模型通常依赖于全局特征对齐和局部特征对齐,但模态间和模态内的相关信息常被忽略。提出了一种基于关系挖掘的跨模态行人重识别方法,该方法包括双流主干网络、负相似度挖掘模块、关系编码器。首先,通过双流主干网络实现了全局和局部特征对齐;其次,通过负相似度挖掘模块提升了图像-文本对特征辨别的细粒度;最后,通过关系编码器模块分别学习图像和文本中隐含的关系信息,实现关系级别的特征对齐。在CUHK-PEDES数据集和ICFG-PEDES数据集上的实验结果证明,文中方法能够达到较高的识别精度。     

一种端到端的个体出行轨迹重识别的深度学习方法

对于行人的再识别研究大多采用图像处理和计算机视觉领域的相关方法,在社会治安领域和商业领域内受到了越来越多的关注.从信息检索的角度出发,提出了一种端到端的深度学习框架,对匿名化的基于位置的服务(LBS)数据进行用户再识别.首先,该框架采用嵌入网络对输入的位置序列及其对应的时间序列进行编码;然后采用递归循环网络对用户每天的...     

不确定广义时变时滞系统的鲁棒H_∞控制

针对具有时变时滞和线性分式参数不确定性广义系统,研究基于状态反馈的鲁棒H∞控制问题.利用增广Lyapunov泛函并结合自由权矩阵方法,保留了Lyapunov泛函导数中的时滞上界信息,得到时变时滞广义系统的一个新的有界实引理(BRL).在此基础上,给出不确定广义时变时滞系统H∞状态反馈控制律的一个直接设计方法.所给结果均以严格线性矩阵不等式(LMI)表示.数值实例表明了结果的有效性和较小保守性.     

基于特定深度内部学习网络提高"不理想"图像分辨率

现有基于深度学习的图像分辨率提升方法中需耗费大量时间训练,且受限于特定的训练数据等问题。本文引入“零射击”超分辨率概念,可以重复利用已有照片、噪声图像、生物数据以及获取过程未知或非理想的其他图像的相关内部信息,以提高其分辨率。在测试阶段训练一个小的图像特定卷积神经网络,仅需对从输入图像本身提取的示例进行训练；然后通过单个图像内部信息再现,进一步利用图像内部相关信息,以增强图像分辨率。实验结果表明,本文算法可以加快训练速度且不需要标准训练集,图像分辨率优于现有基于卷积神经网络的超分辨率方法,以及已有的无监督超分辨率方法。     

基于局部结构保持的高维数据半监督深度嵌入聚类算法

聚类是机器学习和数据挖掘中的重要课题。近年来,深度神经网络(Deep Neural Networks,DNN)在各种聚类任务中受到广泛关注。特别是半监督聚类,在大量无监督数据中仅引入少量先验信息即可显著提高聚类性能。然而,这些聚类方法忽略了定义的聚类损失可能破坏特征空间,从而导致非代表性的无意义特征。针对现有半监督深度聚类的特征学习过程中局部结构保持有所欠缺的问题,本文提出一种改进的半监督深度嵌入聚类(Improved Semi-supervised Deep Embedded Clustering,ISDEC)算法,采用欠完备自动编码器在特征表达学习的同时,保持数据的内在局部结构;通过综合聚类损失、成对约束损失和重构损失,对聚类标签分配和特征表达进行联合优化。在包括基因数据在内的若干高维数据集上的实验结果表明,本方法的聚类性能比现有方法更好。     

利用增量式非线性流形学习的状态监测方法

针对传统流形学习方法难以处理大批量设备运行数据的特点,提出了一种采用增量式流形学习方法的机械设备状态监测方法.该方法首先利用局部切空间排列算法对训练样本集进行非线性维数约简,得到初始的低维流形结构,然后通过增量式学习机制对新增的时序样本点进行动态聚类.通过对压缩机喘振试验数据及滚动轴承故障数据的分析表明,该方法的计算复杂度低,可以有效地识别出隐藏在高维特征集中的非线性故障特征,因此具有良好的工程应用前景.     

A Hybrid Unsupervised Clustering-Based Anomaly Detection Method

In recent years, machine learning-based cyber intrusion detection methods have gained increasing popularity. The number and complexity of new attacks continue to rise; therefore, effective and intelligent solutions are necessary. Unsupervised machine learning techniques are particularly appealing to intrusion detection systems since they can detect known and unknown types of attacks as well as zero-day attacks. In the current paper,we present an unsupervised anomaly detection method, which combines Sub-Space Clustering(SSC) and One Class Support Vector Machine(OCSVM) to detect attacks without any prior knowledge. The proposed approach is evaluated using the well-known NSL-KDD dataset. The experimental results demonstrate that our method performs better than some of the existing techniques.