哈希图半监督学习方法及其在图像分割中的应用

图半监督学习(Graph based semi-supervised learning, GSL)方法需要花费大量时间构造一个近邻图, 速度比较慢. 本文提出了一种哈希图半监督学习(Hash graph based semi-supervised learning, HGSL)方法, 该方法通过局部敏感的哈希函数进行近邻搜索, 可以有效降低图半监督学习方法所需的构图时间. 图像分割实验表明, 该方法一方面可以达到更好的分割效果, 使分割准确率提高0.47%左右; 另一方面可以大幅度减小分割时间, 以一幅大小为300像素×800像素的图像为例, 分割时间可减少为图半监督学习所需时间的28.5%左右.     

基于双模型交互学习的半监督医学图像分割

在医学图像中,器官或病变区域的精准分割对疾病诊断等临床应用有着至关重要的作用,然而分割模型的训练依赖于大量标注数据.为减少对标注数据的需求,本文主要研究针对医学图像分割的半监督学习任务.现有半监督学习方法广泛采用平均教师模型,其缺点在于,基于指数移动平均(Exponential moving average, EMA)的参数更新方式使得老师模型累积学生模型的错误知识.为避免上述问题,提出一种双模型交互学习方法,引入像素稳定性判断机制,利用一个模型中预测结果更稳定的像素监督另一个模型的学习,从而缓解了单个模型的错误经验的累积和传播.提出的方法在心脏结构分割、肝脏肿瘤分割和脑肿瘤分割三个数据集中取得优于前沿半监督方法的结果.在仅采用30%的标注比例时,该方法在三个数据集上的戴斯相似指标(Dice similarity coefficient, DSC)分别达到89.13%, 94.15%, 87.02%.     

基于半监督学习的眉毛图像分割方法

眉毛图像的分割,由于受到毛发、姿势及个体差异的影响,是一个非常困难的问题。提出了一种利用半监督学习技术进行彩色眉毛图像分割的方法,首先通过手工在眉毛图像上简单画上几条线标注部分眉毛点和非眉毛点,然后利用半监督学习技术完成眉毛图像分割并从中提取纯眉毛图像,最后通过实验说明该方法具有非常好的分割效果,可用于眉毛识别的前期预处理。     

基于编码器-解码器的半监督图像语义分割

基于深度卷积神经网络的图像语义分割方法需要大量像素级标注的训练数据,但标注的过程费时又费力.本文基于生成对抗网络提出一种编码-解码结构的半监督图像语义分割方法,其中编码器-解码器模块作为生成器,整个网络通过耦合标准多分类交叉熵损失和对抗损失进行训练.为充分利用浅层网络包含的丰富的语义信息,本文将编码器中不同尺度的特征输入到分类器,并将得到的不同粒度的分类结果融合,进而优化目标边界.此外,鉴别器通过发现无标签数据分割结果中的可信区域,以此提供额外的监督信号,来实现半监督学习.在PASCAL VOC 2012和Cityscapes上的实验表明,本文提出的方法优于现有的半监督图像语义分割方法.     

基于生成对抗网络的自动细胞核分割半监督学习方法

为了减少对标注图像数量的依赖,提出一种新颖的半监督学习方法用于细胞核的自动分割。首先,通过新的卷积神经网络（CNN）从背景中自动提取细胞区域。其次,判别器网络通过应用全卷积网络来为输入的图像生成置信图;同时耦合对抗性损失和标准交叉熵损失,以改善分割网络的性能。最后,将标记图像和无标记图像与置信图结合来训练分割网络,使分割网络可以在提取的细胞区域中识别单个细胞核。对84张图像（训练集中的1/8图像带标注,其余图像无标注）的实验结果表明,提出的细胞核分割方法的分割准确率度量（SEG）得分可以达到77.9%,F1得分可以达到76.0%,这比该方法使用670张图像且训练集中的所有图像都带标注时的表现要好。     

基于生成对抗网络的自动细胞核分割半监督学习方法

为了减少对标注图像数量的依赖，提出一种新颖的半监督学习方法用于细胞核的自动分割。首先，通过新的卷积神经网络（CNN）从背景中自动提取细胞区域。其次，判别器网络通过应用全卷积网络来为输入的图像生成置信图；同时耦合对抗性损失和标准交叉熵损失，以改善分割网络的性能。最后，将标记图像和无标记图像与置信图结合来训练分割网络，使分割网络可以在提取的细胞区域中识别单个细胞核。对84张图像（训练集中的1/8图像带标注，其余图像无标注）的实验结果表明，提出的细胞核分割方法的分割准确率度量（SEG）得分可以达到77.9%，F1得分可以达到76.0%，这比该方法使用670张图像且训练集中的所有图像都带标注时的表现要好。     

基于跨任务一致性的半监督肝脏CT图像分割

目前基于深度学习的医学图像分割方法往往需要大量带标记数据训练网络模型,然而医学影像的标记数据获取通常非常昂贵,半监督学习能使模型利用大量未标记数据和少量标记数据学习。该文提出了一种基于跨任务一致性的半监督学习框架来降低神经网络模型训练时需要的标记数据成本。该方法利用V-Net网络作为主干框架并添加两个辅助解码器,同时在解码器中引入一个辅助回归任务,提高模型分割性能,并在主副解码器的分割任务和回归任务之间施加正则化约束的跨任务一致性损失,该框架能够学习到大量未标记数据的几何先验信息。在LiTS2017 Challenges数据集上验证了该方法的有效性。在使用20%标记数据的实验中,该方法的Dice系数和Jaccard指数分别达到了93.95%和88.87%,相比全监督V-Net网络模型训练下的Dice系数和Jaccard系数分别提高了3.60百分点和5.78百分点。实验结果表明,该方法在使用少量带标记数据情况下达到接近100%带标记数据训练分割肝脏的精度,与其他的半监督方法相比分割精度更优。     

基于半监督的3D肝脏CT自动分割方法研究

肝癌是常见癌症之一,有着较高的死亡率,精准分割肝癌区域是辅助诊断治疗的重要前提。然而肝脏CT图像需要专业的医师进行标注,有标签数据较少,获取途径单一。针对分割腹部肝脏CT图像需要大量高质量标签并且较难获取的问题,提出了一种采用协同训练的半监督学习分割方法。首先,将有标签数据输入3D U-Net和3D Res U-Net进行有监督训练,保存训练得到的两个分割模型,在两个分割模型中分别对无标签数据进行预测;然后,挑选预测的结果,再加入全连接条件随机场处理挑选出的伪标签,细化伪标签的边缘信息,提升伪标签的精确度;最后,加入到训练集中,重复上述步骤直到分割结果的Dice相似系数停止提升时结束训练。实验在LiTS2017 Challenge肝脏数据集上进行测试,结果表明,在有标签数据集占总数据集的30%时,该方法的Dice值达到90.22%,几乎与全监督3D Res U-Net分割结果持平,说明该半监督学习方法是有效的。     

基于局部尺度转换的拉普拉斯核方法

采用数据点的结构信息可以提高半监督学习的性能。为此,提出一种基于图的半监督学习方法。利用局部尺度转换对不同密度区域中的边权重设置不同的尺度参数,在此基础上构造图的拉普拉斯核分类器进行分类学习。在多个数据集上的实验显示该方法优于其他基于核的半监督分类方法。     

细化Transformer网络的弱监督图像语义分割

图像级标签的弱监督图像语义分割方法是目前比较热门的研究方向,类激活图生成方式是最为常用的解决该类问题的主要工作方法。由于类激活图的稀疏性,导致判别区域的准确性降低。针对上述问题,提出了一种改进的Transformer网络弱监督图像学习方法。首先,引入空间注意力交换层来扩大类激活图的覆盖范围;其次,进一步设计了一个注意力自适应模块,来指导模型增强弱区域的类响应;特别地,在类生成过程中,构建了一个自适应跨域来提高模型分类性能。该方法在Pascal VOC 2012 验证集和测试集上分别达到了73.5%和73.0%。实验结果表明,细化Transformer网络学习方法有助于提高弱监督图像的语义分割性能。     

基于图的半监督关系抽取

提出利用基于图的半监督学习算法,即标注传递算法,指导计算机从非结构化的文本中自动识别出实体之间的关系.该方法首先利用图策略来建立关系抽取的模型.在这个图模型中,各个有标签和未标签的样本被表示成图上的各个节点,而样本间的距离则作为图上各边的权重.然后,关系抽取的任务就转化成在这个图上估计出一个满足全局一致性假设的标注函数通过对ACE(automatic content extraction)语料库的评测,结果显示,当只有少量的标签样本时,采用该标注传递的方法可以获得比基于SVM(support vector machine)的有监督关系抽取更好的性能,同时也明显优于基于Bootstrapping的半监督关系抽取的方法.     

Instance selection method for improving graph-based semi-supervised learning

Graph-based semi-supervised learning is an important semi-supervised learning paradigm. Although graph-based semi-supervised learning methods have been shown to be helpful in various situations, they may adversely affect performance when using unlabeled data. In this paper, we propose a new graph-based semi-supervised learning method based on instance selection in order to reduce the chances of performance degeneration. Our basic idea is that given a set of unlabeled instances, it is not the best approach to exploit all the unlabeled instances; instead, we should exploit the unlabeled instances that are highly likely to help improve the performance, while not taking into account the ones with high risk. We develop both transductive and inductive variants of our method. Experiments on a broad range of data sets show that the chances of performance degeneration of our proposed method are much smaller than those of many state-of-the-art graph-based semi-supervised learning methods.     

结合均值漂移的基于图的半监督图像分类

针对基于图的半监督流形正则化图像分类算法需要大量无标记样本训练分类器,空间和时间复杂度高,甚至不能处理大规模图像,且对背景或目标复杂的图像分类错误率较高的问题,提出了结合均值漂移（mean shift）的基于图的半监督流形正则化图像分类算法。该方法对基于图的半监督流形正则化分类算法的改进主要体现在两方面,首先是通过mean shift算法对图像进行了平滑,以平滑后的图像作为分类对象;其次不是利用所有无标记样本,而是只采用少量无标记样本。实验结果表明:图像的平滑使得目标和背景区域的特征更为一致,从而利用较少的样本就可以提高分类器的正确率;同时大大降低了算法的复杂度,使得基于图的半监督分类算法用于分类大规模图像成为可能。     

Robust self-tuning semi-supervised learning

We investigate the issue of graph-based semi-supervised learning (SSL). The labeled and unlabeled data points are represented as vertices in an undirected weighted neighborhood graph, with the edge weights encoding the pairwise similarities between data objects in the same neighborhood. The SSL problem can be then formulated as a regularization problem on this graph. In this paper we propose a robust self-tuning graph-based SSL method, which (1) can determine the similarities between pairwise data points automatically; (2) is not sensitive to outliers. Promising experimental results are given for both synthetic and real data sets.     

Interactive image segmentation using probabilistic hypergraphs

This paper introduces a novel interactive framework for segmenting images using probabilistic hypergraphs which model the spatial and appearance relations among image pixels. The probabilistic hypergraph provides us a means to pose image segmentation as a machine learning problem. In particular, we assume that a small set of pixels, which are referred to as seed pixels, are labeled as the object and background. The seed pixels are used to estimate the labels of the unlabeled pixels by learning on a hypergraph via minimizing a quadratic smoothness term formed by a hypergraph Laplacian matrix subject to the known label constraints. We derive a natural probabilistic interpretation of this smoothness term, and provide a detailed discussion on the relation of our method to other hypergraph and graph based learning methods. We also present a front-to-end image segmentation system based on the proposed method, which is shown to achieve promising quantitative and qualitative results on the commonly used GrabCut dataset.     

Learning with Positive and Unlabeled Examples Using Topic-Sensitive PLSA

It is often difficult and time-consuming to provide a large amount of positive and negative examples for training a classification system in many applications such as information retrieval. Instead, users often find it easier to indicate just a few positive examples of what he or she likes, and thus, these are the only labeled examples available for the learning system. A large amount of unlabeled data are easier to obtain. How to make use of the positive and unlabeled data for learning is a critical problem in machine learning and information retrieval. Several approaches for solving this problem have been proposed in the past, but most of these methods do not work well when only a small amount of labeled positive data are available. In this paper, we propose a novel algorithm called Topic-Sensitive pLSA to solve this problem. This algorithm extends the original probabilistic latent semantic analysis (pLSA), which is a purely unsupervised framework, by injecting a small amount of supervision information from the user. The supervision from users is in the form of indicating which documents fit the users' interests. The supervision is encoded into a set of constraints. By introducing the penalty terms for these constraints, we propose an objective function that trades off the likelihood of the observed data and the enforcement of the constraints. We develop an iterative algorithm that can obtain the local optimum of the objective function. Experimental evaluation on three data corpora shows that the proposed method can improve the performance especially only with a small amount of labeled positive data.     

Semisupervised Regression with Cotraining-Style Algorithms

The traditional setting of supervised learning requires a large amount of labeled training examples in order to achieve good generalization. However, in many practical applications, unlabeled training examples are readily available, but labeled ones are fairly expensive to obtain. Therefore, semisupervised learning has attracted much attention. Previous research on semisupervised learning mainly focuses on semisupervised classification. Although regression is almost as important as classification, semisupervised regression is largely understudied. In particular, although cotraining is a main paradigm in semisupervised learning, few works has been devoted to cotraining-style semisupervised regression algorithms. In this paper, a cotraining-style semisupervised regression algorithm, that is, COREG, is proposed. This algorithm uses two regressors, each labels the unlabeled data for the other regressor, where the confidence in labeling an unlabeled example is estimated through the amount of reduction in mean squared error over the labeled neighborhood of that example. Analysis and experiments show that COREG can effectively exploit unlabeled data to improve regression estimates.     

针对不确定正例和未标记学习的最近邻算法(英文)

研究了在正例和未标记样本场景下不确定样本的分类问题,提出了一种新的算法NNPU(nearest neighbor algorithm for positive and unlabeled learning)。NNPU具有两种实现方式:NNPUa和NNPUu。在UCI标准数据集上的实验结果表明,充分考虑数据不确定信息的NNPUu算法要比仅仅考虑样本中不确定信息均值的NNPUa算法具有更好的分类能力;同时,NNPU算法在对精确数据进行分类时,比NN-d、OCC以及aPUNB算法性能更优。     

自适应主动半监督学习方法

主动学习从大量无标记样本中挑选样本交给专家标记.现有的批抽样主动学习算法主要受3个限制：（1）一些主动学习方法基于单选择准则或对数据、模型设定假设,这类方法很难找到既有不确定性又有代表性的未标记样本;（2）现有批抽样主动学习方法的性能很大程度上依赖于样本之间相似性度量的准确性,例如预定义函数或差异性衡量;（3）噪声标签问题一直影响批抽样主动学习算法的性能.提出一种基于深度学习批抽样的主动学习方法.通过深度神经网络生成标记和未标记样本的学习表示和采用标签循环模式,使得标记样本与未标记样本建立联系,再回到相同标签的标记样本.这样同时考虑了样本的不确定性和代表性,并且算法对噪声标签具有鲁棒性.在提出的批抽样主动学习方法中,算法使用的子模块函数确保选择的样本集合具有多样性.此外,自适应参数的优化,使得主动学习算法可以自动平衡样本的不确定性和代表性.将提出的主动学习方法应用到半监督分类和半监督聚类中,实验结果表明,所提出的主动学习方法的性能优于现有的一些先进的方法.