Distributed Active Partial Label Learning

Active learning(AL)trains a high-precision predictor model from small numbers of labeled data by iteratively annotating the most valuable data sample from an unlabeled data pool with a class label throughout the learning process.However,most current AL methods start with the premise that the labels queried at AL rounds must be free of ambiguity,which may be unrealistic in some real-world applications where only a set of candidate labels can be obtained for selected data.Besides,most of the existing AL algorithms only consider the case of centralized processing,which necessitates gathering together all the unlabeled data in one fusion center for selection.Considering that data are collected/stored at different nodes over a network in many real-world scenarios,distributed processing is chosen here.In this paper,the issue of distributed classification of partially labeled(PL)data obtained by a fully decentralized AL method is focused on,and a distributed active partial label learning(dAPLL)algorithm is proposed.Our proposed algorithm is composed of a fully decentralized sample selection strategy and a distributed partial label learning(PLL)algorithm.During the sample selection process,both the uncertainty and representativeness of the data are measured based on the global cluster centers obtained by a distributed clustering method,and the valuable samples are chosen in turn.Meanwhile,using the disambiguation-free strategy,a series of binary classification problems can be constructed,and the corresponding cost-sensitive classifiers can be cooperatively trained in a distributed manner.The experiment results conducted on several datasets demonstrate that the performance of the dAPLL algorithm is comparable to that of the corresponding centralized method and is superior to the existing active PLL(APLL)method in different parameter configurations.Besides,our proposed algorithm outperforms several current PLL methods using the random selection strategy,especially when only small amounts of data are selected to be assigned with the candidate labels.

A Robust Framework for Multimodal Sentiment Analysis with Noisy Labels Generated from Distributed Data Annotation

Multimodal sentiment analysis utilizes multimodal data such as text,facial expressions and voice to detect people’s attitudes.With the advent of distributed data collection and annotation,we can easily obtain and share such multimodal data.However,due to professional discrepancies among annotators and lax quality control,noisy labels might be introduced.Recent research suggests that deep neural networks(DNNs)will overfit noisy labels,leading to the poor performance of the DNNs.To address this challenging problem,we present a Multimodal Robust Meta Learning framework(MRML)for multimodal sentiment analysis to resist noisy labels and correlate distinct modalities simultaneously.Specifically,we propose a two-layer fusion net to deeply fuse different modalities and improve the quality of the multimodal data features for label correction and network training.Besides,a multiple meta-learner(label corrector)strategy is proposed to enhance the label correction approach and prevent models from overfitting to noisy labels.We conducted experiments on three popular multimodal datasets to verify the superiority of ourmethod by comparing it with four baselines.

面向非均匀分布数据的代价敏感标记分布学习

标记歧义近年来在机器学习和数据挖掘领域备受关注.标记分布学习(LDL)通过为样本分配概率标记来解决标记歧义问题.现有的LDL方法主要是为处理训练数据均匀分布的情况而设计的.然而,在实际应用中,训练数据往往呈现非均匀分布.因此,提出了一种代价敏感的标记分布学习方法(CSLDL),用以处理这种非均匀分布的数据.通过充分利用样本的密度信息,设计了一种新的损失函数.首先,将描述度集平均划分为多个区间,并统计这些区间中的样本个数,从而推导出每个类别标记的经验密度向量.其次,为了确保不同区间之间的连续性,利用邻居来对目标区间的经验密度进行修正.将经验密度向量与对称核进行卷积,以使每个区间不仅考虑当前区间,还考虑附近区间.最后,利用修正后的密度向量构建代价矩阵,并结合Kullback-Leibler(K-L)散度来处理非均匀分布的训练数据.CSLDL在10个真实世界的数据集上与6种最先进的算法进行了对比实验.实验结果充分验证了提出的方法的有效性和优越性.

基于深度森林与异质集成的标记分布学习方法

作为一种解决标签模糊性问题的新学习范式,标记分布学习(LDL)近年来受到了广泛的关注.为了进一步提升标记分布学习的预测性能,提出一种联合深度森林与异质集成的标记分布学习方法(LDLDF).所提方法采用深度森林的级联结构模拟具有多层处理结构的深度学习模型,在级联层中组合多个异质分类器增加集成的多样性.相较于其他现有LDL方法,LDLDF能够逐层处理信息,学习更好的特征表示,挖掘数据中丰富的语义信息,具有强大的表示学习能力和泛化能力.此外,考虑到深层模型可能出现的模型退化问题,LDLDF采用一种层特征重用机制(layer feature reuse)降低模型的训练误差,有效利用深层模型每一层的预测能力.大量的实验结果表明,所提方法优于近期的同类方法.

基于语义规则增强的蒙古语情感分布学习

为完善基于先验知识的标记增强方法对于情绪信息的捕捉,提出一种基于语义规则增强的蒙古语情感分布学习方法(semantic rule enhancement based Mongolian emotion distribution learning, SRE-MEDL)。在情感轮和情感词典的基础上,引入程度词典和否定词典,得到各种情感词组合,以此制定相应的语义规则计算情感词权重,将其融入到标记增强中。在情感分布学习中融入从情感分布空间到实例特征空间的反向重构映射来弥补正向映射引起的原始信息丢失问题。对比实验结果显示,在蒙古语和中英文常用数据集上,SRE-MEDL方法在标记增强任务和情感分布学习中的表现均优于现有方法。

Active label distribution learning via kernel maximum mean discrepancy

Label distribution learning(LDL)is a new learning paradigm to deal with label ambiguity and many researches have achieved the prominent performances.Compared with traditional supervised learning scenarios,the annotation with label distribution is more expensive.Direct use of existing active learning(AL)approaches,which aim to reduce the annotation cost in traditional learning,may lead to the degradation of their performance.To deal with the problem of high annotation cost in LDL,we propose the active label distribution learning via kernel maximum mean discrepancy(ALDL-kMMD)method to tackle this crucial but rarely studied problem.ALDL-kMMD captures the structural information of both data and label,extracts the most representative instances from the unlabeled ones by incorporating the nonlinear model and marginal probability distribution matching.Besides,it is also able to markedly decrease the amount of queried unlabeled instances.Meanwhile,an effective solution is proposed for the original optimization problem of ALDL-kMMD by constructing auxiliary variables.The effectiveness of our method is validated with experiments on the real-world datasets.

Label distribution learning for scene text detection

Recently,segmentation-based scene text detection has drawn a wide research interest due to its flexibility in describing scene text instance of arbitrary shapes such as curved texts.However,existing methods usually need complex post-processing stages to process ambiguous labels,i.e.,the labels of the pixels near the text boundary,which may belong to the text or background.In this paper,we present a framework for segmentation-based scene text detection by learning from ambiguous labels.We use the label distribution learning method to process the label ambiguity of text annotation,which achieves a good performance without using additional post-processing stage.Experiments on benchmark datasets demonstrate that our method produces better results than state-of-the-art methods for segmentation-based scene text detection.

Environment Adaptive Deep Learning Classification System Based on One-shot Guidance

When utilizing the deep learning models in some real applications,the distribution of the labels in the environment can be used to increase the accuracy.Generally,to compute this distribution,there should be the validation set that is labeled by the ground truths.On the other side,the dependency of ground truths limits the utilization of the distribution in various environments.In this paper,we carried out a novel system for the deep learning-based classification to solve this problem.Firstly,our system only uses one validation set with ground truths to compute some hyper parameters,which is named as one-shot guidance.Secondly,in an environment,our system builds the validation set and labels this by the prediction results,which does not need any guidance by the ground truths.Thirdly,the computed distribution of labels by the validation set selectively cooperates with the probability of labels by the output of models,which is to increase the accuracy of predict results on testing samples.We selected six popular deep learning models on three real datasets for the evaluation.The experimental results show that our system can achieve higher accuracy than state-of-art methods while reducing the dependency of labeled validation set.

基于多尺度特征融合的图片情感分布学习

视觉情感分析旨在分析人们对视觉刺激的情感反映,近年来受到了共享平台和网络社交等多媒体视觉数据相关领域的关注.传统的图片情感分析侧重于单标签的情感分类,忽略了图片表达的情感的复杂性和图像潜在的情绪分布信息,不能体现出图片所表达的不同情绪之间的相关性.针对以上问题,首先采用ViT和ResNet网络进行全局和局部融合的多尺度情感特征提取,通过主导情绪分类和标签分布学习进行图片情感识别,充分表征图片的复杂情感.在公开的Flickr_LDL数据集和Twitter_LDL数据集上取得了显著的效果,证明了提出方法的有效性.

结合局部标记序关系的弱监督标记分布学习

标记分布学习(label distribution learning,LDL)是一种用于解决标记多义性的新颖学习范式。现有的LDL方法大多基于完整数据信息进行设计,然而由于高昂的标注成本以及标注人员水平的局限性,很难获取到完整标注数据信息,且会导致传统LDL算法性能的下降。为此,本文提出了一种新型的结合局部序标记关系的弱监督标记分布学习算法,通过维持尚未缺失标记之间的相对关系,并利用标记相关性来恢复缺失的标记,在数据标注不完整的情况下提升算法性能。在14个数据集上进行了大量的实验来验证算法的有效性。

基于粒的标记增强标记分布学习

标记分布学习能有效求解多标记学习任务,然而分类器构造以获得大规模具有更强监督信息的标注为前提,在许多应用中难以满足。一种替代的方案是以标记增强的方式从传统逻辑形式的标注中挖掘出隐含的数值型标记的重要程度。现有的标记增强方法大多假设增强后的标记需要在所有示例上保持原有逻辑标记的相关性,不能有效保持局部标记相关性。基于粒计算理论,提出了一种适用于标记分布学习的粒化标记增强学习方法。该方法通过k均值聚类构造具有局部相关性语义的信息粒,并在粒的抽象层面上,分别在图上依据逻辑标记的特性和属性空间的拓扑性质完成粒内示例的标记转化。最后,将得到的标记分布在示例层面进行融合,得到描述整个数据集标记重要程度的数值型标记。大量比较研究表明,所提出的模型可以显著地提升多标记学习的性能。

基于标记分布学习的人脸年龄识别算法

针对人脸年龄识别可用数据集普遍不足的问题,为提升可用数据集不变情况下人脸年龄识别的精度,在深度学习(DL)框架中引入标记分布学习(LDL)策略,命名为DL-LDL,其中卷积神经网络用于自动提取人脸特征,改进的标记分布学习用于学习真实年龄及相邻年龄之间的模糊性和多义性,以丰富年龄信息,提高识别精度.将DL-LDL方法在MORPH和FG-NET这2个公开数据集上进行了试验测试.结果表明:DL-LDL方法提高了年龄识别的精度,与现有最先进的人脸年龄识别方法相比,在MORPH和FG-NET上的平均绝对误差分别降低了8.2%和13.8%.

基于CRF的驾驶员意图在线识别

为提升驾驶辅助系统决策准确率,文章建立一种基于条件随机场(CRF)的驾驶员意图在线识别系统,为驾驶辅助系统提供重要参考。文章采用深度标签分布学习(DLDL)识别驾驶员的头部姿态判断其观察目标,在驾驶模拟器上创建实验场景,采集驾驶员操作数据,按照操作划分并输入至CRF进行训练,识别驾驶员的换道意图。通过实验对比,识别率在96%以上,能够在5 s前识别驾驶员的换道意图。在此基础上实现在线识别,满足实际应用要求。

Soft video parsing by label distribution learning

In this paper, we tackle the problem of segmenting out a sequence of actions from videos. The videos contain background and actions which are usually composed of ordered sub-actions. We refer the sub-actions and the background as semantic units. Considering the possible overlap between two adjacent semantic units, we propose a bidirectional sliding window method to generate the label distributions for various segments in the video. The label distribution covers a certain number of semantic unit labels, representing the degree to which each label describes the video segment. The mapping from a video segment to its label distribution is then learned by a Label Distribution Learning (LDL) algorithm. Based on the LDL model, a soft video parsing method with segmental regular grammars is proposed to construct a tree structure for the video. Each leaf of the tree stands for a video clip of background or sub-action. The proposed method shows promising results on the THUMOST4, MSR-II and UCF101 datasets and its computational complexity is much less than the compared state-of-the-art video parsing method.

Practical age estimation using deep label distribution learning

Age estimation plays an important role in human-computer interaction system.The lack of large number of facial images with definite age label makes age estimation al-gorithms inefficient.Deep label distribution learning(DLDL)which employs convolutional neural networks(CNN)and label distribution learning to learn ambiguity from ground-truth age and adjacent ages,has been proven to outperform current state-of-the-art framework.However,DLDL assumes a rough label distribution which covers all ages for any given age label.In this paper,a more practical label distribution paradigm is proposed:we limit age label distribution that only covers a reasonable number of neighboring ages.In addition,we explore different label distributions to improve the performance of the proposed learning model.We employ CNN and the improved label distribution learning to estimate age.Experimental results show that compared to the DLDL,our method is more effective for facial age recognition.

基于多峰标签分布学习的多任务年龄估计方法

针对面部年龄估计中标签序数信息和类间相关性提取难的问题,提出一种多峰分布(MPD)年龄编码,并基于该年龄编码构建了一个多任务年龄估计方法MPDNet(MPD Network)。首先,利用MPD将年龄标签转化为年龄分布,以提取年龄标签间的相关信息,构建年龄老化趋势的阶段性;然后,采用一个轻量级网络进行多阶段的特征提取,并对提取的特征分别进行标签分布学习(LDL)和回归学习;最后,共享两个学习任务的输出,并在训练过程中通过反向传播互相优化,避免传统标签分布学习中对分布结果直接进行回归导致的误差传播。在MORPHⅡ数据集上的实验结果表明,MPDNet的平均绝对误差(MAE)达到2.67,与基于VGGNets(Visual Geometry Group Networks)构建的DEX(Deep EXpectation)、RankingCNN(Ranking Convolutional Neural Network)等方法相当,而参数仅为VGGNets的1/788.6;而且MPDNet也优于同体量的C3AE(extremely Compact yet efficient Cascade Context-based Age Estimation model)、SSR-Net(Soft Stagewise Regression Network)等方法。MPDNet能够较好地利用年龄标签间丰富的相关信息来提取更具判别力的年龄特征,提高年龄估计任务的预测精度。

基于深度学习多任务与标签分布的年龄估计研究

人脸通常受环境、习惯、基因、性别、种族等内外因素共同影响,因而准确的面部年龄估计是一个很具挑战性的课题。鉴于此,提出一种基于性别辅助任务的双分支年龄估计模型CUT-ResNet50,将标签分布学习应用于年龄估计,探究性别因素对年龄估计任务的影响。通过将共享参数层提取的低级特征输入到性别网络分支以提取性别特征后,再与共享参数层的低级特征融合,作为年龄网络分支的输入。引入标签分布学习,利用数据集相邻样本信息生成年龄的分布信息,减少人脸样本分布不均衡对年龄估计性能的影响,并重新训练双分支年龄估计模型。在公开的MORPH-II数据集与UTKFace数据集上,MAE分别达2.1和4.1,这表明添加了性别辅助任务的多任务学习与标签分布学习可以提升年龄估计准确度,从而证明了新设计模型的有效性。

Multi-label active learning by model guided distribution matching

Multi-label learning is an effective framework for learning with objects that have multiple semantic labels, and has been successfully applied into many real-world tasks, In contrast with traditional single-label learning, the cost of la- beling a multi-label example is rather high, thus it becomes an important task to train an effective multi-label learning model with as few labeled examples as possible. Active learning, which actively selects the most valuable data to query their labels, is the most important approach to reduce labeling cost. In this paper, we propose a novel approach MADM for batch mode multi-label active learning. On one hand, MADM exploits representativeness and diversity in both the feature and label space by matching the distribution between labeled and unlabeled data. On the other hand, it tends to query predicted positive instances, which are expected to be more informative than negative ones. Experiments on benchmark datasets demonstrate that the proposed approach can reduce the labeling cost significantly.

基于局部标记相关性的标记分布学习算法

针对大多数现有的标记分布学习算法从全局角度利用标记相关性,忽略了仅存于部分示例范围内的局部标记相关性,同时,算法性能会受到无关和冗余特征干扰的问题,提出一种基于局部标记相关性的标记分布学习算法(LDL-LLC)。通过对训练数据进行分组,将每组训练数据的标记相关性约束在标记输出上,探索和利用局部标记相关性,引入特征选择常用的范数约束,学习标记私有特征和共享特征。在多个真实标记分布数据集上的对比实验结果表明,LDL-LLC算法性能良好。

腰椎间盘早期退变智能诊断方法研究

分析腰椎间盘早期退变诊断现状及问题,提出基于代谢组学和标签分布学习方法可建立腰椎间盘早期退变分类器,并利用PT-Bayes、AA-BP和SA-IIS算法实施构建,通过实际计算分析各分类器的性能、应用意义及效果。