基于数据分布的聚类联邦学习

联邦学习(federated learning)可以解决分布式机器学习中基于隐私保护的数据碎片化和数据隔离问题。在联邦学习系统中,各参与者节点合作训练模型,利用本地数据训练局部模型,并将训练好的局部模型上传到服务器节点进行聚合。在真实的应用环境中,各节点之间的数据分布往往具有很大差异,导致联邦学习模型精确度较低。为了解决非独立同分布数据对模型精确度的影响,利用不同节点之间数据分布的相似性,提出了一个聚类联邦学习框架。在Synthetic、CIFAR-10和FEMNIST标准数据集上进行了广泛实验。与其他联邦学习方法相比,基于数据分布的聚类联邦学习对模型的准确率有较大提升,且所需的计算量也更少。     

视觉特征对比解耦的广义零样本学习

广义零样本学习通常利用在ImageNet上预训练的深度模型来提取相应的视觉特征,然而预训练模型提取到的视觉特征不可避免地包含和语义无关的信息,这将导致语义—视觉对齐的偏差以及对不可见类的负迁移,从而影响分类结果。为解决上述问题,提出了视觉特征对比解耦的广义零样本学习模型(visual feature contrast decoupling for generalized zero-shot learning, VFCD-GZSL),通过解耦出视觉特征中的语义相关表示来降低冗余信息对分类结果的影响。具体来说,首先用条件变分自编码器生成不可见类的视觉特征。然后通过解耦模块将视觉特征解耦语义相关和语义无关的潜层表示,同时添加总相关惩罚和对比损失来鼓励两者间的相互独立,并用语义关系匹配模型衡量其语义一致性,从而指导模型学习语义相关表示。最后使用特征细化模块细化后的特征和语义相关表示联合学习一个广义零样本学习分类器。在四个数据集上的实验均取得较优的结果,证实了所提方法的有效性。     

基于特征融合的调制识别增强与迁移演化

针对调制识别中单一图像的特征信息不足,区分度不够高,识别范围受限的问题。本文提出了一种基于时频图和星座图特征融合的调制识别特征增强方法,利用深度学习神经网络提取信号图像的特征,构建特征空间,通过多维特征融合,挖掘和整合不同特征的优势,增强模型算法的鲁棒性。此外运用了模型迁移的方法,仅需对分类器进行训练,大幅节约了训练时间和资源,具有很强的实时性和实用性。仿真结果显示,在0db左右的条件下,相比于单一特征图像,采用特征融合增强的方法能将信号的平均识别率提高约25%,通过模型迁移,省去了卷积神经网络的训练,所需的训练时间约为迁移前的9.6%,消耗内存约为迁移前的7.3%,同时模型的识别率损失控制在了5%以内。     

基于特征迭代的云存储数据即时确定性删除方法

传统数据删除方法易受到云存储环境中大量近似特征的影响,产生冗余数据,导致加解密时间过长、密钥可用率较低,为此提出一种基于特征迭代的云存储数据即时确定性删除方法。首先,提取云存储数据中的冗余数据特征,对云存储下冗余数据进行分类,迭代直至收敛,实现冗余数据高性能删除;其次,采用加密机制实现云存储数据在网络用户间的安全共享,将原始数据密文切分为剩余密文和采样密文;最后,把不完整的剩余数据密文上传至云端,同时引入可信任第三方对取样密文进行保存,通过销毁取样密文实现数据即时确定性删除。实验结果表明,所提方法的数据密文拆分所用时间较短,且密钥可用率较高,可达90%,说明其方法能够有效满足云存储系统中对冗余数据或过期数据的确定性删除要求。     

基于多判据的散乱点云特征点提取算法

为了有效获取散乱点云中的尖锐特征点和边界特征点,提出一种利用多判据融合的特征点提取算法。首先利用一种改进的k-d tree构建点云拓扑,搜索样点的K局部邻域;然后利用法向夹角判定准则、核密度判定准则、场力和判定准则分别求取各个样点局部邻域的三个特征参数,最后通过加权计算特征参数得到每个样点的特征值与全局判定阈值,特征值比阈值大的点即为特征点。实验证明,该算法能有效的获取散乱点云中边沿特征点与尖锐特征点。     

基于CMFS-MIC特征选择的跳频电台个体识别方法

针对跳频电台细微特征集中存在冗余特征等导致电台识别时存在计算量大、识别准确率低等问题,提出了一种基于CMFS-MIC特征选择的跳频电台个体识别方法。首先计算采集到的各个跳频电台信号样本的细微特征集,然后采用关联信息熵度量特征子集的组合效应,兼顾考虑特征间的关联关系和冗余关系对各个特征进行降序排序。在此基础上,采用最大信息系数度量的近似马尔可夫毯方法删除冗余特征,实现对特征子集进行优化和降维。最后,设计了投票组合分类器实现对4部跳频电台信号的识别。仿真结果表明,本文算法具有更高的分选识别率。     

Discriminative multi-task objects tracking with active feature selection and drift correction

In this paper, we propose a discriminative multi-task objects tracking method with active feature selection and drift correction. The developed method formulates object tracking in a particle filter framework as multi-Task discriminative tracking. As opposed to generative methods that handle particles separately, the proposed method learns the representation of all the particles jointly and the corresponding coefficients are similar. The tracking algorithm starts from the active feature selection scheme, which adaptively chooses suitable number of discriminative features from the tracked target and background in the dynamic environment. Based on the selected feature space, the discriminative dictionary is constructed and updated dynamically. Only a few of them are used to represent all the particles at each frame. In other words, all the particles share the same dictionary templates and their representations are obtained jointly by discriminative multi-task learning. The particle that has the highest similarity with the dictionary templates is selected as the next tracked target state. This jointly sparsity and discriminative learning can exploit the relationship between particles and improve tracking performance. To alleviate the visual drift problem encountered in object tracking, a two-stage particle filtering algorithm is proposed to complete drift correction and exploit both the ground truth information of the first frame and observations obtained online from the current frame. Experimental evaluations on challenging sequences demonstrate the effectiveness, accuracy and robustness of the proposed tracker in comparison with state-of-the-art algorithms.     

Multi-resolution feature fusion for face recognition

For face recognition, image features are first extracted and then matched to those features in a gallery set. The amount of information and the effectiveness of the features used will determine the recognition performance. In this paper, we propose a novel face recognition approach using information about face images at higher and lower resolutions so as to enhance the information content of the features that are extracted and combined at different resolutions. As the features from different resolutions should closely correlate with each other, we employ the cascaded generalized canonical correlation analysis (GCCA) to fuse the information to form a single feature vector for face recognition. To improve the performance and efficiency, we also employ “Gabor-feature hallucination”, which predicts the high-resolution (HR) Gabor features from the Gabor features of a face image directly by local linear regression. We also extend the algorithm to low-resolution (LR) face recognition, in which the medium-resolution (MR) and HR Gabor features of a LR input image are estimated directly. The LR Gabor features and the predicted MR and HR Gabor features are then fused using GCCA for LR face recognition. Our algorithm can avoid having to perform the interpolation/super-resolution of face images and having to extract HR Gabor features. Experimental results show that the proposed methods have a superior recognition rate and are more efficient than traditional methods.     

大冶硫酸四系列干吸塔结构特点

以干燥塔为例，介绍大冶公司硫酸四系列干吸塔的结构特点。除捕沫层简体及出气管为316L不锈钢外，其余塔体均为碳钢内衬瓷砖结构。塔底为球形底，中心排酸。采用槽管式分酸器，分酸点密度为43个/m^2，设可调闸板以保证各槽酸量均匀；闸板外设置带孔板的分布板，以消除进口酸的冲击，保证槽内酸液面平稳。比较了该塔与常规塔的不同之处，强调了设备节点的优化设计。     

Skeleton-enhanced line drawings for 3D models

We present a novel line drawing approach for 3D models by introducing their skeleton information into the rendering process. Based on the silhouettes of the input 3D models, we first extract feature lines in geometric regions by utilizing their curvature, torsion and view-dependent information. Then, the skeletons of the models are extracted by our newly developed skeleton extraction algorithm. After that, we draw the skeleton-guided lines from non-geometric regions through the skeleton information. These lines are combined with the feature lines to render the final line drawing result using the line optimization. Experimental results show that our algorithm can render line drawings more effectively with enhanced skeletons. The resulting artistic effects can capture the local geometries as well as the global skeletons of the input 3D models.