In this study, we propose a global optimization algorithm based on quantizing the energy level of an objective function in an NP-hard problem. According to the white noise hypothesis for a quantization error with a dense and uniform distribution, we can regard the quantization error as i.i.d. white noise. From stochastic analysis, the proposed algorithm converges weakly only under conditions satisfying Lipschitz continuity, instead of local convergence properties such as the Hessian constraint of the objective function. This shows that the proposed algorithm ensures global optimization by Laplace's condition. Numerical experiments show that the proposed algorithm outperforms conventional learning methods in solving NP-hard optimization problems such as the traveling salesman problem.
translated by 谷歌翻译
在本文中,我们提出了一种量化的学习方程,具有对所提出的算法的量化和随机分析的单调增加分辨率。根据致密且均匀分布的量化误差的白噪声假设,我们可以将量化误差视为i.i.d. \白噪声。基于此,我们表明,具有单调增加量化分辨率的学习方程作为分布观点略微收敛。本文的分析表明,全局优化对于满足Lipschitz条件的域,而不是局部会聚属性,例如客观函数的Hessian约束。
translated by 谷歌翻译
Human organs constantly undergo anatomical changes due to a complex mix of short-term (e.g., heartbeat) and long-term (e.g., aging) factors. Evidently, prior knowledge of these factors will be beneficial when modeling their future state, i.e., via image generation. However, most of the medical image generation tasks only rely on the input from a single image, thus ignoring the sequential dependency even when longitudinal data is available. Sequence-aware deep generative models, where model input is a sequence of ordered and timestamped images, are still underexplored in the medical imaging domain that is featured by several unique challenges: 1) Sequences with various lengths; 2) Missing data or frame, and 3) High dimensionality. To this end, we propose a sequence-aware diffusion model (SADM) for the generation of longitudinal medical images. Recently, diffusion models have shown promising results on high-fidelity image generation. Our method extends this new technique by introducing a sequence-aware transformer as the conditional module in a diffusion model. The novel design enables learning longitudinal dependency even with missing data during training and allows autoregressive generation of a sequence of images during inference. Our extensive experiments on 3D longitudinal medical images demonstrate the effectiveness of SADM compared with baselines and alternative methods.
translated by 谷歌翻译
Accurately extracting driving events is the way to maximize computational efficiency and anomaly detection performance in the tire frictional nose-based anomaly detection task. This study proposes a concise and highly useful method for improving the precision of the event extraction that is hindered by extra noise such as wind noise, which is difficult to characterize clearly due to its randomness. The core of the proposed method is based on the identification of the road friction sound corresponding to the frequency of interest and removing the opposite characteristics with several frequency filters. Our method enables precision maximization of driving event extraction while improving anomaly detection performance by an average of 8.506%. Therefore, we conclude our method is a practical solution suitable for road surface anomaly detection purposes in outdoor edge computing environments.
translated by 谷歌翻译
尽管最近的凝视估计方法非常重视从面部或眼睛图像中提取与目光相关的特征,但如何定义包括凝视相关组件在内的特征是模棱两可的。这种模糊性使该模型不仅学习了与之相关的功能,而且还学会了无关紧要的功能。特别是,这对于跨数据库的性能是致命的。为了克服这个具有挑战性的问题,我们提出了一种基于数据驱动的方法,该方法具有数据驱动的方法,该方法具有生成的对抗网络反转的分解特征,以选择性地利用潜在代码中的目光相关特征。此外,通过利用基于GAN的编码器生成过程,我们将输入图像从目标域转移到源域图像,而凝视估计器充分了解了。此外,我们建议在编码器中凝视失真损失,以防止凝视信息的失真。实验结果表明,我们的方法在跨域凝视估计任务中实现了最新的凝视估计精度。该代码可在https://github.com/leeisack/latentgaze/上找到。
translated by 谷歌翻译
尽管已经通过深度学习技术开发了凝视估计方法,但没有采取诸如以50像素或更少的像素宽度或更少的像素宽度的低分辨率面部图像中准确性能的方法。为了在具有挑战性的低分辨率条件下解决限制,我们提出了高频专注的超级分辨凝视估计网络,即Haze-Net。我们的网络改善了输入图像的分辨率,并通过基于高频注意力块提出的超级分辨率模块增强了眼睛特征和这些边界。此外,我们的凝视估计模块利用眼睛的高频组件以及全球外观图。我们还利用面部的结构位置信息来近似头姿势。实验结果表明,即使在具有28x28像素的低分辨率面部图像中,提出的方法也表现出强大的凝视估计性能。该工作的源代码可在https://github.com/dbseorms16/haze_net/上获得。
translated by 谷歌翻译
网络安全研究中的关键主题之一是自动COA(行动)攻击搜索方法。被动搜索攻击的传统COA攻击方法可能很困难,尤其是随着网络变大。为了解决这些问题,正在开发新的自动COA技术,其中,本文设计了一种智能的空间算法,以在可扩展网络中有效运行。除空间搜索外,还考虑了基于蒙特卡洛(MC)的时间方法来照顾时间变化的网络行为。因此,我们为可扩展和时变网络的时空攻击COA搜索算法提出了一个时空攻击。
translated by 谷歌翻译
我们提出了一种预测搜索查询项目关系的有效方法。我们结合了预训练的变压器和LSTM模型,并使用对抗性训练,指数移动平均值,多样采样的辍学和基于多样性的集合来提高模型鲁棒性,以解决一个非常困难的问题,即预测以前从未见过的查询。我们所有的策略都集中在提高深度学习模型的鲁棒性上,并适用于使用深度学习模型的任何任务。采用我们的策略,我们在KDD CUP 2022产品替换分类任务中获得了第十名。
translated by 谷歌翻译
编码器模型是用于医学图像分割的常用深神网络(DNN)模型。常规编码器模型使像素的预测重点放在像素周围的本地模式上。这使得对维护对象的形状和拓扑的细分进行分割变得具有挑战性,这通常需要了解对象的全局背景。在这项工作中,我们提出了一个傅立叶系数分割网络〜(FCSN),这是一个基于DNN的新型模型,该模型通过学习对象掩模的复杂傅立叶系数来分割对象。傅立叶系数是通过在整个轮廓上集成来计算的。因此,为了使我们的模型对系数进行精确的估计,该模型的动机是要整合对象的全局环境,从而更准确地分割了对象的形状。这种全球环境意识也使我们的模型在推理期间没有看到的本地扰动,例如医学图像中普遍存在的添加噪声或运动模糊。将FCSN与3个医疗图像分割任务(ISIC \ _2018,RIM \ _CUP,RIM \ _disc)进行比较时,FCSN的Hausdorff得分明显降低19.14(iSIC \ _2018,RIM \ _CUP,RIM \ _disc) 6个任务分别为6 \%),17.42(6 \%)和9.16(14 \%)。此外,FCSN可以通过丢弃解码器模块轻巧,从而产生了大量的计算开销。 FCSN仅需要比UNETR和DEEPLABV3+的参数222m,82m和10m。 FCSN的推理和训练速度为1.6ms/img和6.3ms/img,即8 $ \ times $和3 $ \ times $ $ \ times $比UNET和UNETR快。
translated by 谷歌翻译
诊断阿尔茨海默氏病(AD)涉及故意诊断过程,这是由于其先天性的不可逆性特征和微妙而逐渐发展。这些特征使AD生物标志物从结构性脑成像(例如结构MRI)扫描非常具有挑战性。此外,很有可能与正常衰老纠缠在一起。我们通过使用临床引导的原型学习,通过可解释的AD可能性图估计(XADLIME)提出了一种新颖的深度学习方法,用于在3D SMRIS上进行AD进展模型。具体而言,我们在潜在临床特征的簇上建立了一组拓扑感知的原型,发现了AD光谱歧管。然后,我们测量潜在临床特征和完善的原型之间的相似性,估计“伪”可能性图。通过将此伪图视为丰富的参考,我们采用估计网络来估算3D SMRI扫描的AD可能性图。此外,我们通过从两个角度揭示了可理解的概述:临床和形态学,促进了这种可能性图的解释性。在推断期间,这张估计的似然图可以替代看不见的SMRI扫描,以有效地执行下游任务,同时提供彻底的可解释状态。
translated by 谷歌翻译