壁画图像分类中的分组多实例学习方法

针对壁画图像具有较大类内差异的特点,提出一种分组策略,将样本空间划分为不同的子空间,每一个子空间中的所有训练样本训练分类器模型,测试阶段,根据测试样本落到的子空间来选择不同的分类模型对测试样本进行分类。在各个子空间训练分类器时,为了克服壁画图像较强背景噪音的影响,我们将每一幅壁画图像样本看作多个实例的组成,采用多实例学习的方式来训练分类器。训练过程中,我们引入隐变量用于标识每一个实例,隐变量的存在使得分类器的优化问题不是一个凸问题,因此我们无法用梯度下降法去直接求解,本文中我们采用迭代的方式训练Latent SVM作为每一个子空间的分类器。实验证明了本文的分类模型能够较大程度的解决壁画图像的类内差异以及背景噪音对分类结果造成的影响。     

Online multiple instance boosting for object detection

Semi-supervised or unsupervised, incremental learning approaches based on online boosting are very popular for object detection. However, in the course of online learning, since the positive examples labelled by the current classifier may actually not be “correct”, the optimal weak classifier is unlikely to be selected by previous approaches. This would directly lead to a decline in algorithm performance. In this paper, we present an improved online multiple instance learning algorithm based on boosting (called OMILBoost) for object detection. It can pick out the real correct image patch around labelled example with high possibility and thus, avoid drifting problem effectively. Furthermore, our method shows high performance when dealing with partial occlusions. Effectiveness is experimentally demonstrated on six representative video sequences.     

G3P-MI: A genetic programming algorithm for multiple instance learning

This paper introduces a new Grammar-Guided Genetic Programming algorithm for resolving multi-instance learning problems. This algorithm, called G3P-MI, is evaluated and compared to other multi-instance classification techniques in different application domains. Computational experiments show that the G3P-MI often obtains consistently better results than other algorithms in terms of accuracy, sensitivity and specificity. Moreover, it makes the knowledge discovery process clearer and more comprehensible, by expressing information in the form of IF-THEN rules. Our results confirm that evolutionary algorithms are very appropriate for dealing with multi-instance learning problems.     

ReliefF-MI: An extension of ReliefF to multiple instance learning

In machine learning the so-called curse of dimensionality, pertinent to many classification algorithms, denotes the drastic increase in computational complexity and classification error with data having a great number of dimensions. In this context, feature selection techniques try to reduce dimensionality finding a new more compact representation of instances selecting the most informative features and removing redundant, irrelevant, and/or noisy features. In this paper, we propose a filter-based feature selection method for working in the multiple-instance learning scenario called ReliefF-MI; it is based on the principles of the well-known ReliefF algorithm. Different extensions are designed and implemented and their performance checked in multiple instance learning. ReliefF-MI is applied as a pre-processing step that is completely independent from the multi-instance classifier learning process and therefore is more efficient and generic than wrapper approaches proposed in this area. Experimental results on five benchmark real-world data sets and 17 classification algorithms confirm the utility and efficiency of this method, both statistically and from the point of view of execution time.     

Multiple instance learning with bag dissimilarities

Multiple instance learning (MIL) is concerned with learning from sets (bags) of objects (instances), where the individual instance labels are ambiguous. In this setting, supervised learning cannot be applied directly. Often, specialized MIL methods learn by making additional assumptions about the relationship of the bag labels and instance labels. Such assumptions may fit a particular dataset, but do not generalize to the whole range of MIL problems. Other MIL methods shift the focus of assumptions from the labels to the overall (dis)similarity of bags, and therefore learn from bags directly. We propose to represent each bag by a vector of its dissimilarities to other bags in the training set, and treat these dissimilarities as a feature representation. We show several alternatives to define a dissimilarity between bags and discuss which definitions are more suitable for particular MIL problems. The experimental results show that the proposed approach is computationally inexpensive, yet very competitive with state-of-the-art algorithms on a wide range of MIL datasets.     

用于组织病理图像分类的双层多实例学习模型

目的 分析组织病理学全玻片图像（whole slide images,WSIs）是病理学诊断的金标准。WSIs具有千兆像素,且通常缺乏像素级标注。弱监督多实例学习是分析WSIs的主流方法,其关键是怎样从大量实例中精确识别出触发类别预测的关键实例。以前的WSIs分析方法主要是在独立同分布假设下设计的,忽略了实例间的相关性和肿瘤的异质性。针对上述问题,提出一种新的双层多实例学习模型。方法 具体地,提出的模型由自适应特征挖掘器和双路交叉检测模块级联构成。首先,第1层的自适应特征挖掘器检索包中的区分性特征,为后续的实例特征聚合生成可靠的内部查询;然后,第2层的双路交叉检测模块通过建模内部查询与实例间的相关性,聚合包中所有实例生成最终的包级表示。此外,在特征提取部分中引入了自监督对比学习方法SimCLR以生成高质量的实例特征。结果在两个公共可用的数据集CAMELYON-16和TCGA(the cancer genome atlas)肺癌上评估了提出的模型,对比分析6种经典的多实例学习模型,结果显示本文模型的性能最优。在准确率方面,所提方法在CAMELYON-16和TCGA肺癌两个数据集上分别达到...     

在线多示例学习目标跟踪方法研究

多示例学习是不同于传统机器学习的一种新的学习模式,近年来被应用于图像检索、文本分类等领域。提出一种基于在线学习的多示例学习算法,将其应用于目标跟踪。该算法通过构造一个在线学习的多示例分类器作为检测器,无需制作大量的样本进行离线的训练,只需在第一帧手动选中目标,便可以自动生成正样本和负样本,并在随后的帧序列中,根据跟踪到的目标自动更新分类器,在跟踪器丢失目标或者目标从场景中消失后,它能够重新检测到目标并更新跟踪器,从而有效地支持了跟踪器跟踪目标。实验证明该方法在背景复杂,光线变化,摄像机抖动等复杂条件下,可以很好地跟踪到目标,且对遮挡具有较好的鲁棒性。     

基于高效多示例学习的目标跟踪

基于多示例学习(MIL)的跟踪算法能在很大程度上缓解漂移问题。然而,该算法的运行效率相对较低,精度也有待提高,这是由于MIL算法采用的强分类器更新策略效率不高,以及分类器更新速度与目标外观变化速度不一致引起的。为此提出一种新的强分类器更新策略,以大幅提升MIL算法的运行效率;同时提出一种动态更新分类器学习率的机制,使更新后的分类器更符合目标的外观,提高跟踪算法的精度。通过实验将该算法和MIL算法以及基于加权多示例学习的跟踪算法(WMIL)进行对比,实验结果表明,所提出算法的运行效率和跟踪精度都是三者中最好的,在背景中没有与被跟踪目标外观相似的干扰物体存在时有较好的跟踪优势。     

特征加权融合的在线多示例学习跟踪算法

为了能更加准确鲁棒地跟踪目标,提出了特征加权融合的在线多示例学习跟踪算法（WFMIL）。WFMIL在多示例学习框架下分别训练两种特征（Hog和Haar）分类器。在跟踪过程中,通过线性运算融合成一个强分类器,同时在学习过程中对正包中的示例引入权重。实验结果统计表明WFMIL能很好地解决目标漂移问题,并且对目标遮挡、运动突变、光照变化以及运动模糊等具有较好的鲁棒性。     

基于RGB-D的在线多示例学习目标跟踪算法

基于2D特征的目标跟踪算法缺少3维信息,因此在目标尺度、姿态变化和平面旋转时会引起跟踪不稳定易丢失目标的问题,为此提出一种基于RGB‐D的在线多示例学习目标跟踪算法。利用深度数据的特性在深度图中和RGB图中构建多尺度空间,提取多尺度的 Haar‐D特征和 Haar特征;利用多实例学习策略将多尺度的 Haar‐D特征和 Haar特征融合。实验结果表明,该算法能很好得处理室内或室外环境下目标姿态变化、平面旋转和部分遮挡的问题。     

基于深度学习的实例分割研究综述

深度学习在计算机视觉领域已经取得很大发展,虽然基于深度学习的实例分割研究近年来才成为研究热点,但其技术可广泛应用在自动驾驶,辅助医疗和遥感影像等领域。实例分割作为计算机视觉的基础问题之一,不仅需要对不同类别目标进行像素级别分割,还要对不同目标进行区分。此外,目标形状的灵活性,不同目标间的遮挡和繁琐的数据标注问题都使实例分割任务面临极大的挑战。本文对实例分割中一些具有价值的研究成果按照两阶段和单阶段两部分进行了系统性的总结,分析了不同算法的优缺点并对比了模型在COCO数据集上的测试性能,归纳了实例分割在特殊条件下的应用,简要介绍了常用数据集和评价指标。最后,对实例分割未来可能的发展方向及其面临的挑战进行了展望。     

在线特征选取的多示例学习目标跟踪

目的 传统的多示例学习跟踪在跟踪过程中使用了自学习过程,当目标跟踪失败时分类器很容易退化。针对这个问题,提出一种基于在线特征选取的多示例学习跟踪方法(MILOFS)。方法 首先,该文使用稀疏随机矩阵来简化视频跟踪中图像特征的构建,使用随机矩阵投影来自高维度的图像信息。然后,利用Fisher线性判别模型构建包模型的损失函数,依照示例响应值直接在示例水平构建分类器的判别模型。最后,从梯度下降角度看待在线增强模型,使用梯度增强法来构建分类器的选取模型。结果 对不同场景的图像序列进行对比实验,实验结果中在线自适应增强(OAB)、在线多实例学习跟踪(MILTrack)、加权多实例学习跟踪(WMIL)、在线特征选取多实例学习跟踪(MILOFS)的平均跟踪误差分别为36像素、23像素、24像素、13像素,本文算法在光照变化、发生遮挡,以及形变的情况下都能准确跟踪目标,且具有很高的实时性。结论 基于在线特征选取的多示例学习跟踪,跟踪过程使用梯度增强法并直接在示例水平构建包模型的判别模型,可以有效克服传统多示例学习中的分类器退化问题。     

基于随机局部均值Hash特征的在线学习目标跟踪

在局部遮挡,光线变化,以及复杂背景环境下进行有效稳定的目标跟踪一直是一个长期困扰研究者的复杂问题。提出一种基于随机局部均值Hash特征的在线学习目标跟踪算法,算法的创新点为基于泊松概率分布的目标模型建立及其在线更新。算法首先利用已标定实际位置的目标图像来初始化目标模型及构建初始分类器池,由此求出下一帧的检测算子,同时基于多实例在线学习方法,利用检测到的目标样本（正样本）以及附近的背景样本（负样本）在线更新目标模型,求出新的检测算子用于后续帧的目标检测及跟踪。提出的算法与现有基于检测学习的OnlineBoostingTracker,SemiTracker,BeyondSemiTracker,Context Tracker和MILTracker跟踪算法在给定的四个标准视频序列中进行了跟踪性能比较。实验结果表明,在各种复杂环境下,该算法具备良好的综合跟踪性能,尤其在抗局部遮挡方面尤为突出。在抗目标旋转方面,该算法仍有待优化。     

A multiple instance learning based framework for semantic image segmentation

Most image segmentation algorithms extract regions satisfying visual uniformity criteria. Unfortunately, because of the semantic gap between low-level features and high-level semantics, such regions usually do not correspond to meaningful parts. This has motivated researchers to develop methods that, by introducing high-level knowledge into the segmentation process, can break through the performance ceiling imposed by the semantic gap. The main disadvantage of those methods is their lack of flexibility due to the assumption that such knowledge is provided in advance. In content-based image retrieval (CBIR), relevance feedback (RF) learning has been successfully applied as a technique aimed at reducing the semantic gap. Inspired by this, we present a RF-based CBIR framework that uses multiple instance learning to perform a semantically-guided context adaptation of segmentation parameters. A partial instantiation of this framework that uses mean shift-based segmentation is presented. Experiments show the effectiveness and flexibility of the proposed framework on real images.     

基于遗传规划和主动学习的本体实例匹配

针对现有实例匹配方法存在的准确率和学习效率不高的问题,提出了一种新的基于遗传规划和主动学习的链接规则学习方法,并用于本体实例匹配。设计了更合理的链接规则表示,并针对链接规则的特点,对遗传规划的初始种群产生、适应度函数和进化算子进行了详细设计。提出了一种考虑样本相关性的主动学习采样策略,使得稀有样本被优先训练。实验结果表明,该方法不仅学习效率更高,而且能够学习出高质量的链接规则,取得了较好的本体实例匹配结果。     

多通道Haar-like特征多示例学习目标跟踪

目的 提出一种基于多通道Haar-like特征的多示例学习目标跟踪算法,克服了多示例跟踪算法在处理彩色视频时利用信息少和弱特征不能更换的缺点。方法 首先,针对原始多示例学习跟踪算法对彩色视频帧采用单通道信息或将其简单转化为灰度图像进行跟踪会丢失部分特征信息的缺点,提出在RGB三通道上生成位置、大小和通道完全随机的Haar-like特征来更好地表示目标。其次,针对多示例学习跟踪算法中Haar-like弱特征不能更换,难以反映目标自身和外界条件变化的特点,提出在弱分类器选择过程中,用随机生成的新Haar-like特征实时替换部分判别力最弱的Haar-like特征,从而在目标模型中引入新的信息,以适应目标外观的动态变化。结果 对8个具有挑战性的彩色视频序列的实验结果表明,与原始多示例学习跟踪算法、加权多示例学习跟踪算法、基于分布场的跟踪算法相比,提出的方法不仅获得了最小的平均中心误差,而且平均跟踪准确率比上述3种算法分别高52.85%,34.75%和5.71%,在4种算法中获得最优性能。结论 通过将Haar-like特征从RGB三通道随机生成,并将判别力最弱的部分Haar-like弱特征实时更换,显著提升了原始多示例学习跟踪算法对彩色视频的跟踪效果,扩展了其应用前景。     

基于哈希学习的投票样例选择算法

随着数据的海量型增长,如何存储并利用数据成为目前学术研究和工业应用等方面的热门问题。样例选择是解决此类问题的方法之一,它在原始数据中依据既定规则选出代表性的样例,从而有效地降低后续工作的难度。基于此,提出一种基于哈希学习的投票样例选择算法。首先通过主成分分析（PCA）方法将高维数据映射到低维空间;然后利用k-means算法结合矢量量化方法进行迭代运算,并将数据用聚类中心的哈希码表示;接着将分类后的数据按比例进行随机选择,在多次独立运行算法后投票选择出最终的样例。与压缩近邻（CNN）算法和大数据线性复杂度样例选择算法LSH-IS-F相比,所提算法在压缩比方面平均提升了19%。所提算法思想简单容易实现,能够通过调节参数自主控制压缩比。在7个数据集上的实验结果显示所提算法在测试精度相似的情况下在压缩比和运行时间方面较随机哈希有较大优势。     

基于聚类和实例硬度的入侵检测过采样方法

针对由于网络流量数据不平衡而导致入侵检测模型检测率低的问题,提出了一种基于聚类和实例硬度的入侵检测过采样方法(CHO).首先,测算少数类数据对应的硬度值并作为输入,即计算其近邻样本中多数类的样本所占的比例;接下来,运用Canopy聚类方法对少数类数据进行预聚类,将所得到的聚类数值作为K-means++聚类方法的聚类参数...     

An EM based multiple instance learning method for image classification

In this paper, we propose an EM based learning algorithm to provide a comprehensive procedure for maximizing the measurement of diverse density on given multiple Instances. Furthermore, the new EM based learning framework converts an MI problem into a single-instance treatment by using EM to maximize the instance responsibility for the corresponding label of each bag. To learn a desired image class, a user may select a set of exemplar images and label them to be conceptual related (positive) or conceptual unrelated (negative) images. A positive image consists of at least one object that the user may be interested, and a negative image should not contain any object that the user may be interested. By using the proposed EM based learning algorithm, an image retrieval prototype system is implemented. Experimental results show that for only a few times of relearning cycles, the prototype system can retrieve user’s favor images from WWW over Internet.     

Towards a unified multi-source-based optimization framework for multi-label learning

In the era of Big Data, a practical yet challenging task is to make learning techniques more universally applicable in dealing with the complex learning problem, such as multi-source multi-label learning. While some of the early work have developed many effective solutions for multi-label classification and multi-source fusion separately, in this paper we learn the two problems together, and propose a novel method for the joint learning of multiple class labels and data sources, in which an optimization framework is constructed to formulate the learning problem, and the result of multi-label classification is induced by the weighted combination of the decisions from multiple sources. The proposed method is responsive in exploiting the label correlations and fusing multi-source data, especially in the fusion of long-tail data. Experiments on various multi-source multi-label data sets reveal the advantages of the proposed method.