Process mining is a methodology for the derivation and analysis of process models based on the event log. When process mining is employed to analyze business processes, the process discovery step, the conformance checking step, and the enhancements step are repeated. If a user wants to analyze a process from multiple perspectives (such as activity perspectives, originator perspectives, and time perspectives), the above procedure, inconveniently, has to be repeated over and over again. Although past studies involving process mining have applied detailed stepwise methodologies, no attempt has been made to incorporate and optimize multi-perspective process mining procedures. This paper contributes to developing a solution approach to this problem. First, we propose an automatic discovery framework of a multi-perspective process model based on deep Q-Learning. Our Dual Experience Replay with Experience Distribution (DERED) approach can automatically perform process model discovery steps, conformance check steps, and enhancements steps. Second, we propose a new method that further optimizes the experience replay (ER) method, one of the key algorithms of deep Q-learning, to improve the learning performance of reinforcement learning agents. Finally, we validate our approach using six real-world event datasets collected in port logistics, steel manufacturing, finance, IT, and government administration. We show that our DERED approach can provide users with multi-perspective, high-quality process models that can be employed more conveniently for multi-perspective process mining.
translated by 谷歌翻译
The time-series forecasting (TSF) problem is a traditional problem in the field of artificial intelligence. Models such as Recurrent Neural Network (RNN), Long Short Term Memory (LSTM), and GRU (Gate Recurrent Units) have contributed to improving the predictive accuracy of TSF. Furthermore, model structures have been proposed to combine time-series decomposition methods, such as seasonal-trend decomposition using Loess (STL) to ensure improved predictive accuracy. However, because this approach is learned in an independent model for each component, it cannot learn the relationships between time-series components. In this study, we propose a new neural architecture called a correlation recurrent unit (CRU) that can perform time series decomposition within a neural cell and learn correlations (autocorrelation and correlation) between each decomposition component. The proposed neural architecture was evaluated through comparative experiments with previous studies using five univariate time-series datasets and four multivariate time-series data. The results showed that long- and short-term predictive performance was improved by more than 10%. The experimental results show that the proposed CRU is an excellent method for TSF problems compared to other neural architectures.
translated by 谷歌翻译
发型转移是将源发型修改为目标的任务。尽管最近的发型转移模型可以反映发型的精致特征,但它们仍然有两个主要局限性。首先,当源和目标图像具有不同的姿势(例如,查看方向或面部尺寸)时,现有方法无法转移发型,这在现实世界中很普遍。同样,当源图像中有非平凡的区域被其原始头发遮住时,先前的模型会产生不切实际的图像。当将长发修改为短发时,肩膀或背景被长发遮住了。为了解决这些问题,我们为姿势不变的发型转移,发型提出了一个新颖的框架。我们的模型包括两个阶段:1)基于流动的头发对齐和2)头发合成。在头发对齐阶段,我们利用基于关键点的光流估计器将目标发型与源姿势对齐。然后,我们基于语义区域感知的嵌入面膜(SIM)估计器在头发合成阶段生成最终的发型转移图像。我们的SIM估计器将源图像中的封闭区域划分为不同的语义区域,以反映其在涂料过程中的独特特征。为了证明我们的模型的有效性,我们使用多视图数据集(K-Hairstyle和Voxceleb)进行定量和定性评估。结果表明,发型通过在不同姿势的图像之间成功地转移发型来实现最先进的表现,而这是以前从未实现的。
translated by 谷歌翻译
While 3D GANs have recently demonstrated the high-quality synthesis of multi-view consistent images and 3D shapes, they are mainly restricted to photo-realistic human portraits. This paper aims to extend 3D GANs to a different, but meaningful visual form: artistic portrait drawings. However, extending existing 3D GANs to drawings is challenging due to the inevitable geometric ambiguity present in drawings. To tackle this, we present Dr.3D, a novel adaptation approach that adapts an existing 3D GAN to artistic drawings. Dr.3D is equipped with three novel components to handle the geometric ambiguity: a deformation-aware 3D synthesis network, an alternating adaptation of pose estimation and image synthesis, and geometric priors. Experiments show that our approach can successfully adapt 3D GANs to drawings and enable multi-view consistent semantic editing of drawings.
translated by 谷歌翻译
以前的无监督句子嵌入研究集中在数据增强方法上,例如辍学和基于规则的句子转换方法。但是,这些方法限制了控制句子增强观点的细粒语义。这导致监督信号不足以捕获类似句子的语义相似性。在这项工作中,我们发现使用邻居句子可以捕获相似句子之间更准确的语义相似性。基于这一发现,我们提出了RankEncoder,该发现使用了输入句子和语料库中的句子之间的关系来训练无监督的句子编码器。我们从三个角度评估rankencoder:1)语义文本相似性性能,2)相似句子对的功效,以及3)rankencoder的普遍性。实验结果表明,与先前的最新性能相比,Rankencoder达到80.07 \%Spearman的相关性,绝​​对提高了1.1%。在类似的句子对上,改进更加显着,改善了1.73%。另外,我们证明了RankEncoder普遍适用于现有的无监督句子编码器。
translated by 谷歌翻译
由于发型的复杂性和美味,编辑发型是独一无二的,而且具有挑战性。尽管最近的方法显着改善了头发的细节,但是当源图像的姿势与目标头发图像的姿势大不相同时,这些模型通常会产生不良的输出,从而限制了其真实世界的应用。发型是一种姿势不变的发型转移模型,可以减轻这种限制,但在保留精致的头发质地方面仍然表现出不令人满意的质量。为了解决这些局限性,我们提出了配备潜在优化和新呈现的局部匹配损失的高性能姿势不变的发型转移模型。在stylegan2潜在空间中,我们首先探索目标头发的姿势对准的潜在代码,并根据本地风格匹配保留了详细纹理。然后,我们的模型对源的遮挡构成了对齐的目标头发的遮挡,并将两个图像混合在一起以产生最终输出。实验结果表明,我们的模型在在较大的姿势差异和保留局部发型纹理下转移发型方面具有优势。
translated by 谷歌翻译
对于现实和生动的着色,最近已经利用了生成先验。但是,由于其表示空间有限,因此这种生成先验的野外复杂图像通常会失败。在本文中,我们提出了BigColor,这是一种新型的着色方法,可为具有复杂结构的不同野外图像提供生动的着色。虽然先前的生成先验训练以综合图像结构和颜色,但我们在关注颜色合成之前就学会了一种生成颜色,鉴于图像的空间结构。通过这种方式,我们减轻了从生成先验中合成图像结构的负担,并扩大其表示空间以覆盖各种图像。为此,我们提出了一个以Biggan启发的编码生成网络,该网络使用空间特征映射而不是空间框架的Biggan潜在代码,从而产生了扩大的表示空间。我们的方法可以在单个正向传球中为各种输入提供强大的着色,支持任意输入分辨率,并提供多模式着色结果。我们证明,BigColor明显优于现有方法,尤其是在具有复杂结构的野外图像上。
translated by 谷歌翻译
联合学习(FL)是一种新颖的学习范式,可解决集中学习的隐私泄漏挑战。但是,在FL中,具有非独立和相同分布(非IID)特征的用户可能会恶化全局模型的性能。具体而言,由于非IID数据,全局模型受到权重差异的挑战。为了应对上述挑战,我们提出了机器学习(ML)模型(FIDDIF)的新型扩散策略,以通过非IID数据最大化FL性能。在FedDif中,用户通过D2D通信将本地模型传播给相邻用户。 FedDif使本地模型能够在参数聚合之前体验不同的分布。此外,从理论上讲,我们证明了FedDif可以规避体重差异挑战。在理论的基础上,我们提出了ML模型的沟通效率扩散策略,该策略可以决定基于拍卖理论的学习绩效和沟通成本之间的权衡。绩效评估结果表明,与非IID设置相比,FedDIF将全球模型的测试准确性提高了11%。此外,与最新方法相比
translated by 谷歌翻译
基于图像的虚拟试验旨在综合一个穿给定服装的人的图像。为了解决任务,现有的方法会经过衣物项目,以适合该人的身体并生成穿着该物品的人的分割图,然后再将物品与人融合。但是,当扭曲和分割生成阶段在没有信息交换的情况下单独运行时,扭曲的衣服和分割图之间的未对准发生了,从而导致最终图像中的工件。信息断开还会导致在身体部位遮住的衣服区域附近过度翘曲,所谓的像素 - 刺式伪像。为了解决这些问题,我们提出了一个新颖的尝试条件发生器,作为两个阶段的统一模块(即扭曲和分割生成阶段)。条件生成器中新提出的特征融合块实现了信息交换,并且条件生成器不会造成任何未对准或像素 - 平方形工件。我们还介绍了歧视者的拒绝,从而滤除了不正确的细分图预测并确保虚拟试验框架的性能。高分辨率数据集上的实验表明,我们的模型成功处理了未对准和遮挡,并显着优于基线。代码可从https://github.com/sangyun884/hr-viton获得。
translated by 谷歌翻译
尽管运动补偿大大提高了视频质量,但单独执行运动补偿和视频脱张需要大量的计算开销。本文提出了一个实时视频Deblurring框架,该框架由轻巧的多任务单元组成,该单元以有效的方式支持视频脱张和运动补偿。多任务单元是专门设计的,用于使用单个共享网络处理两个任务的大部分,并由多任务详细网络和简单的网络组成,用于消除和运动补偿。多任务单元最大程度地减少了将运动补偿纳入视频Deblurring的成本,并实现了实时脱毛。此外,通过堆叠多个多任务单元,我们的框架在成本和过度质量之间提供了灵活的控制。我们通过实验性地验证了方法的最先进的质量,与以前的方法相比,该方法的运行速度要快得多,并显示了实时的实时性能(在DVD数据集中测量了30.99db@30fps)。
translated by 谷歌翻译