基于张量表示的域适配的迁移学习中特征表示方法

本文提出一种新的基于张量表示的域适配迁移学习中的特征表示方法,即融合联合域对齐和适配正则化的基于张量表示的迁移学习特征表示方法.当源域和目标域差异很大时,仅将源域对齐潜在共享空间,会造成数据扭曲过大.为缓解此问题,本文方法提出联合域对齐,即源域和目标域同时对齐共享子空间.并且本文方法将适配正则化引入张量表示空间求解.本文适配正则化包括动态分布对齐和图适配,以缩小域间分布差异和保留样本间流行一致性.最后融合联合域对齐,动态分布对齐和图适配,通过联合优化求解获得共享子空间表示.几个公共的跨域数据集上的大量实验结果表明了本文方法优于其它主流的迁移学习方法,验证了本文方法的有效性.     

基于生成对抗网络的无监督域适应分类模型

生成适应模型利用生成对抗网络实现模型结构,并在领域适应学习上取得了突破.但其部分网络结构缺少信息交互,且仅使用对抗学习不足以完全减小域间距离,从而使分类精度受到影响.为此,提出一种基于生成对抗网络的无监督域适应分类模型（Unsupervised Domain Adaptation classification model based on GAN,UDAG）.该模型通过联合使用生成对抗网络和多核最大均值差异度量准则优化域间差异,并充分利用无监督对抗训练及监督分类训练之间的信息传递以学习源域分布和目标域分布之间的共享特征.通过在四种域适应情况下的实验结果表明,UDAG模型学习到更优的共享特征嵌入并实现了域适应图像分类,且分类精度有明显提高.     

基于子空间对齐与自适应CSP算法的运动想象脑电信号分类

在脑机接口中,让分类器从一个用户适应到另一个用户是具有挑战性的,但对于减少新用户的训练时间是必要的.但由于每个个体的神经信号存在着差异,常用的特征提取方法训练的分类器,应用于不同的用户时,准确率很低.因此本文提出了一种新的自适应共空间模式的特征提取方法,该算法通过选择合适的候选试验更新协方差矩阵,然后对提取的特征进行子...     

Sample selection for visual domain adaptation via sparse coding

Visual domain adaptation has attracted much attention and has made great achievement in recent years. It deals with the problem of distribution divergence between source and target domains. Current methods mostly focus on transforming images from different domains into a common space to minimize the distribution divergence. However, there are many irrelevant source samples for target domain even after the transformation. In order to eliminate the irrelevant samples, we develop a sample selection algorithm using sparse coding theory. We do the sample selection in a common subspace of source and target data to find as many as relevant source samples. In the common subspace, data characteristics are preserved by using graph regularization. Therefore, we can select the most relevant samples for our target image classification task. Moreover, in order to build a discriminative classifier for the target domain, we use not only the common part of source and target domains learned in the common subspace but also the specific part of target domain. The algorithm can be extended to handle samples from multiple source domains. Experimental results show that our visual domain adaptation method on the image classification tasks can be very effective for the state-of-the-art datasets.     

一种基于伪标签的半监督少样本学习模型

如何将带有大量标记数据的源域知识模型迁移至带有少量标记数据的目标域是少样本学习研究领域的热点问题.针对现有的少样本学习算法在源域数据与目标域数据的特征分布差异较大时存在的泛化能力较弱的问题,提出一种基于伪标签的半监督少样本学习模型FSLSS（Few-Shot Learning based on Semi-Supervised）.首先,利用pytorch深度学习框架建立一个关系型深度学习网络,并使用源域数据对网络进行预训练;然后,使用此网络对目标域数据进行分类预测,将分类概率最大的类标签作为数据的伪标签;最后,利用目标域的伪标签数据和源域的真实标签数据对网络进行混合训练,并重复伪标签标记与混合训练过程.实验结果表明,相对于现有主流少样本学习算法,FSLSS模型有更好的泛化能力及知识迁移效果.     

A weakly supervised large margin domain adaptation method for isolated handwritten digit recognition

Learning handwriting categories fail to perform well when trained and tested on data from different databases. In this paper, we propose a novel large margin domain adaptation algorithm which is able to learn a transformation between training and test datasets in addition to adapting the parameters of classifier using a few or even no training labeled samples from target handwriting dataset. Additionally, we developed a framework of ensemble projection feature learning for datasets representation as a front end for our algorithm to utilize the abundant unlabeled samples in target domain. Experiments on different handwritten digit datasets adaptations demonstrate that the proposed large margin domain adaptation algorithm achieves superior classification accuracy comparing with the state of the art methods. Quantitative evaluation of the proposed algorithm shows that semi-supervised adaptation utilizing one sample per class of target domain set reduces the error rates by 64.72% comparing with a corresponding SVM classifier.     

基于ELM理论的昆虫分类

机器视觉技术应用在昆虫分类领域,取代传统人眼观察识别过程、提高了工作效率。自动识别技术包含昆虫特征提取和分类器设计两个主要步骤。根据整个识别过程,文中提出了一种基于混合特征的ELM理论昆虫识别方法。在特征提取阶段,提取混合特征包括颜色特征、形态特征、空域纹理特征和频谱纹理特征。在分类器设计阶段采用具有学习速度快且泛化性能好的极限学习机。实验结果表明,该方法使昆虫识别的正确率达到97%,且分类器训练时间短,优于传统的自动识别方法。     

Semi-Supervised Bilinear Subspace Learning

Recent research has demonstrated the success of tensor based subspace learning in both unsupervised and supervised configurations (e.g., 2-D PCA, 2-D LDA, and DATER). In this correspondence, we present a new semi-supervised subspace learning algorithm by integrating the tensor representation and the complementary information conveyed by unlabeled data. Conventional semi-supervised algorithms mostly impose a regularization term based on the data representation in the original feature space. Instead, we utilize graph Laplacian regularization based on the low-dimensional feature space. An iterative algorithm, referred to as adaptive regularization based semi-supervised discriminant analysis with tensor representation (ARSDA/T), is also developed to compute the solution. In addition to handling tensor data, a vector-based variant (ARSDA/V) is also presented, in which the tensor data are converted into vectors before subspace learning. Comprehensive experiments on the CMU PIE and YALE-B databases demonstrate that ARSDA/T brings significant improvement in face recognition accuracy over both conventional supervised and semi-supervised subspace learning algorithms.     

结合多特征融合和极限学习机的红外图像目标分类方法

针对红外图像目标分类问题,提出了结合多特征融合和极限学习机（extreme learning machine,ELM）的方法。采用主成分分析（principal component analysis,PCA）、局部二值模式（local binary pattern,LBP）以及尺度不变特征变换（scale-invariant feature transform,SIFT）三类特征分别描述红外图像中目标的像素分布、局部纹理以及特征点信息。三类特征从不同侧面反映红外图像目标特性,因此具有互为补充的优势。在此基础上,基于多重集典型相关分析（multiset canonical correlations analysis,MCCA）对三类特征进行融合处理,获得统一的特征矢量。融合后的特征不仅继承了原始三类特征的鉴别特性,还有效去除了冗余信息。分类过程中,采用极限学习机作为基础分类器对融合特征矢量进行分类。极限学习机具有参数少、效率高、精度高和稳健性强等显著特点,有利于提高红外目标分类的整体性能。因此,所提出的方法通过结合多特征和极限学习机的优势综合提升了目标识别性能。在实验过程中,采用四类飞机目标的红外图像对所提出方法进行了性能测试。根据与现有几类方法的对比,实验结果证明了提出方法的性能优势。     

基于K-means聚类的子结构相关适配迁移学习方法

域漂移严重影响了传统机器学习方法的性能,现有的领域自适应方法主要通过全局、类级或样本级分布匹配自适应地调整跨域表示。但全局匹配和类级匹配过于粗糙会导致自适应不足,而样本级匹配受到噪声的影响可能导致过度自适应。基于此,提出了一种基于K均值（K-means）聚类的子结构相关适配（SCOAD）迁移学习算法,首先通过K-means聚类分别获得源域和目标域的多个子域,其次寻求子域中心二阶统计量的匹配,最后利用子域内结构对目标域样本进行分类。该方法在传统方法的基础上进一步提高了源域与目标域之间知识迁移的性能。在常用迁移学习数据集上的实验结果表明了所提方法的有效性。     

Robotic grasping recognition using multi-modal deep extreme learning machine

Recognizing which part of an object is graspable or not is important for intelligent robot to perform some complicated tasks. In order to obtain good grasping performance, learning rich representations efficiently from multi-modal RGB-D images is crucial. To address this problem, in this paper, we propose an effective multi-modal deep extreme learning machine structure. In this structure, unsupervised hierarchical extreme learning machine (ELM) is conducted for feature extraction for RGB and depth modalities separately. Then, the shared layer is developed by combining both RGB and depth features. Finally, the ELM is used as supervised feature classifier for final decision. Experimental validation on Cornell grasping dataset illustrates that the proposed multiple modality fusion method achieves better grasp recognition performance.     

基于随机子空间和AdaBoost的自适应集成方法

如何构造差异性大且精确度高的基分类器是集成学习的重点,为此提出一种新的集成学习方法——利用PSO寻找使得AdaBoost依样本权重抽取的数据集分类错误率最小化的最优特征权重分布,依据此最优权重分布对特征随机抽样生成随机子空间,并应用于AdaBoost的训练过程中.这就在增加分类器间差异性的同时保证了基分类器的准确度.最后用多数投票法融合各基分类器的决策结果,并通过仿真实验验证该方法的有效性.     

基于域与样例平衡的多源迁移学习方法

针对如何有效使用多源域的决策知识去预测目标域样例标签的问题，提出一种平衡域与样例信息的多源迁移学习算法.为实现上述目的，本文提出了一种基于域与样例平衡的多源迁移学习方法（Multi-source Transfer Learning by Balancing both Domains and Instances，MTL-BDI）.该方法的基本思想是将域层面和样例层面的双加权平衡项嵌入到迁移学习的原始目标函数中，然后利用交替优化技术对提出的目标函数进行有效求解.在文本和图像数据集上的大量实验表明，该方法在分类精度方面确实优于现有的多源迁移学习方法MCC-SVM（Multiple Convex Combination of SVM）、A-SVM（Adaptive SVM）、Multi-KMM（Multiple Kernel Mean Matching）和DAM（Domain Adaptation Machine）.     

Efficient radar target classification using adaptive jointtime-frequency processing

This paper presents a new target recognition scheme via adaptive Gaussian representation, which uses adaptive joint time-frequency processing techniques. The feature extraction stage of the proposed scheme utilizes the geometrical moments of the adaptivity spectrogram. For this purpose, we have derived exact and closed form expressions of geometrical moments of the adaptive spectrogram in the time, frequency, and joint time-frequency domains. Features obtained by this method can provide substantial savings of computational resources, preserving as much essential information for classifying targets as possible. Next, a principal component analysis is used to further reduce the dimension of feature space, and the resulting feature vectors are passed to the classifier stage based on the multilayer perceptron neural network. To demonstrate the performance of the proposed scheme, various thin-wire targets are identified. The results show that the proposed technique has a significant potential for use in target recognition     

基于分块CNN的多尺度SAR图像目标分类算法

针对合成孔径雷达（Synthetic Aperture Radar, SAR）图像目标分辨率差异大,多尺度SAR图像目标分类准确率不高的问题,提出了一种基于迁移学习和分块卷积神经网络（Convolutional Neural Network, CNN）的SAR图像目标分类算法。首先通过大量与目标域相近的源域数据对分块CNN的参数进行训练,得到不同尺度下的CNN特征提取网络;其次将CNN的卷积和池化层迁移到新的网络结构中,实现目标特征的提取;最后用超限学习机（Extreme Learning Machine, ELM）网络对提取的特征进行分类。实验数据采用美国MSTAR数据库以及多尺度SAR图像舰船目标数据集,实验结果表明,该方法对多尺度SAR图像的分类效果优于传统CNN。     

Projected Transfer Sparse Coding for cross domain image representation

Sparse coding has been used for image representation successfully. However, when there is considerable variation between source and target domain, sparse coding cannot achieve satisfactory results. In this paper, we proposed a Projected Transfer Sparse Coding algorithm. In order to reduce their distribution difference, we project source and target data into a shared low dimensional space. Meanwhile, we learn a projection matrix and a shared dictionary and the sparse coding of source and target data in the low dimensional space. Unlike existing methods, the sparse representations are learnt using the projected data which are invariant to the distribution difference and the irrelevant samples. Thus, the sparse representations are robust and can improve the classification performance. We do not need to know any explicit correspondence across domains. We learn the projection matrix, the discriminative sparse representations, and the dictionary in a unified objective function. Our image representation method yields state-of-the-art results.     

基于注意力机制与迁移学习的乳腺钼靶肿块分类

针对乳腺钼靶图像中良恶性肿块难以诊断的问题,提出一种基于注意力机制与迁移学习的乳腺钼靶肿块分类方法,并用于医学影像中乳腺钼靶肿块的良恶性分类.首先,构建一种新的网络模型,该模型将注意力机制CBAM(Convolutional Block Attention Module)与残差网络ResNet50相结合,用于提高网络对...     

Confidence based class weight and embedding discrepancy constraint network for partial domain adaptation

Partial domain adaptation (PDA) is a special domain adaptation task where the label space of the target domain is a subset of the source domain. In this work, we present a novel adversarial PDA method named Confidence Based Class Weight and Embedding Discrepancy Constraint Network (CEN). Specifically, we design a robust weighting scheme that takes sample confidence and class information into account. It can automatically distinguish outlier samples in the source domain and reduce their importance. Besides, we consider the relationship between feature norm and domain shift. We limit the expectation of the feature norms of both domains to an adaptive value. By this means, we can align the feature distributions and help the deep model learn domain-invariant representations. Comprehensive experiments on three domain adaptation datasets Office-31, Office-home, and Visda2017 show that our approach surpasses state-of-the-art methods on various PDA tasks.