Parallel evolutionary algorithms (PEAs) have been studied for reducing the execution time of evolutionary algorithms by utilizing parallel computing. An asynchronous PEA (APEA) is a scheme of PEAs that increases computational efficiency by generating a new solution immediately after a solution evaluation completes without the idling time of computing nodes. However, because APEA gives more search opportunities to solutions with shorter evaluation times, the evaluation time bias of solutions negatively affects the search performance. To overcome this drawback, this paper proposes a new parent selection method to reduce the effect of evaluation time bias in APEAs. The proposed method considers the search frequency of solutions and selects the parent solutions so that the search progress in the population is uniform regardless of the evaluation time bias. This paper conducts experiments on multi-objective optimization problems that simulate the evaluation time bias. The experiments use NSGA-III, a well-known multi-objective evolutionary algorithm, and compare the proposed method with the conventional synchronous/asynchronous parallelization. The experimental results reveal that the proposed method can reduce the effect of the evaluation time bias while reducing the computing time of the parallel NSGA-III.
translated by 谷歌翻译
Classification bandits are multi-armed bandit problems whose task is to classify a given set of arms into either positive or negative class depending on whether the rate of the arms with the expected reward of at least h is not less than w for given thresholds h and w. We study a special classification bandit problem in which arms correspond to points x in d-dimensional real space with expected rewards f(x) which are generated according to a Gaussian process prior. We develop a framework algorithm for the problem using various arm selection policies and propose policies called FCB and FTSV. We show a smaller sample complexity upper bound for FCB than that for the existing algorithm of the level set estimation, in which whether f(x) is at least h or not must be decided for every arm's x. Arm selection policies depending on an estimated rate of arms with rewards of at least h are also proposed and shown to improve empirical sample complexity. According to our experimental results, the rate-estimation versions of FCB and FTSV, together with that of the popular active learning policy that selects the point with the maximum variance, outperform other policies for synthetic functions, and the version of FTSV is also the best performer for our real-world dataset.
translated by 谷歌翻译
For arbitrary two probability measures on real d-space with given means and variances (covariance matrices), we provide lower bounds for their total variation distance.
translated by 谷歌翻译
The long-standing theory that a colour-naming system evolves under the dual pressure of efficient communication and perceptual mechanism is supported by more and more linguistic studies including the analysis of four decades' diachronic data from the Nafaanra language. This inspires us to explore whether artificial intelligence could evolve and discover a similar colour-naming system via optimising the communication efficiency represented by high-level recognition performance. Here, we propose a novel colour quantisation transformer, CQFormer, that quantises colour space while maintaining the accuracy of machine recognition on the quantised images. Given an RGB image, Annotation Branch maps it into an index map before generating the quantised image with a colour palette, meanwhile the Palette Branch utilises a key-point detection way to find proper colours in palette among whole colour space. By interacting with colour annotation, CQFormer is able to balance both the machine vision accuracy and colour perceptual structure such as distinct and stable colour distribution for discovered colour system. Very interestingly, we even observe the consistent evolution pattern between our artificial colour system and basic colour terms across human languages. Besides, our colour quantisation method also offers an efficient quantisation method that effectively compresses the image storage while maintaining a high performance in high-level recognition tasks such as classification and detection. Extensive experiments demonstrate the superior performance of our method with extremely low bit-rate colours. We will release the source code soon.
translated by 谷歌翻译
我们提出了一种轻巧,准确的方法,用于检测视频中的异常情况。现有方法使用多个实体学习(MIL)来确定视频每个段的正常/异常状态。最近的成功研​​究认为,学习细分市场之间的时间关系很重要,以达到高精度,而不是只关注单个细分市场。因此,我们分析了近年来成功的现有方法,并发现同时学习所有细分市场确实很重要,但其中的时间顺序与实现高准确性无关。基于这一发现,我们不使用MIL框架,而是提出具有自发机制的轻质模型,以自动提取对于确定所有输入段正常/异常非常重要的特征。结果,我们的神经网络模型具有现有方法的参数数量的1.3%。我们在三个基准数据集(UCF-Crime,Shanghaitech和XD-Violence)上评估了方法的帧级检测准确性,并证明我们的方法可以比最新方法实现可比或更好的准确性。
translated by 谷歌翻译
自动故障检测是许多运动的主要挑战。在比赛中,裁判根据规则在视觉上判断缺点。因此,在判断时确保客观性和公平性很重要。为了解决这个问题,一些研究试图使用传感器和机器学习来自动检测故障。但是,与传感器的附件和设备(例如高速摄像头)相关的问题,这些问题与裁判的视觉判断以及故障检测模型的可解释性相抵触。在这项研究中,我们提出了一个用于非接触测量的断层检测系统。我们使用了根据多个合格裁判的判断进行训练的姿势估计和机器学习模型,以实现公平的错误判断。我们使用智能手机视频在包括东京奥运会的奖牌获得者中,使用了正常比赛的智能手机视频,并有意地走路。验证结果表明,所提出的系统的平均准确度超过90%。我们还透露,机器学习模型根据种族步行规则检测到故障。此外,奖牌获得者的故意故障步行运动与大学步行者不同。这一发现符合更通用的故障检测模型的实现。该代码和数据可在https://github.com/szucchini/racewalk-aijudge上获得。
translated by 谷歌翻译
现有的视频域改编(DA)方法需要存储视频帧的所有时间组合或配对源和目标视频,这些视频和目标视频成本昂贵,无法扩展到长时间的视频。为了解决这些局限性,我们建议采用以下记忆高效的基于图形的视频DA方法。首先,我们的方法模型每个源或目标视频通过图:节点表示视频帧和边缘表示帧之间的时间或视觉相似性关系。我们使用图形注意力网络来了解单个帧的重量,并同时将源和目标视频对齐到域不变的图形特征空间中。我们的方法没有存储大量的子视频,而是仅构建一个图形,其中一个视频的图形注意机制,从而大大降低了内存成本。广泛的实验表明,与最先进的方法相比,我们在降低内存成本的同时取得了卓越的性能。
translated by 谷歌翻译
图像恢复算法(例如超级分辨率(SR))是低质量图像中对象检测的必不可少的预处理模块。这些算法中的大多数假定降解是固定的,并且已知先验。但是,实际上,实际降解或最佳的上采样率是未知或与假设不同的,导致预处理模块和随之而来的高级任务(例如对象检测)的性能恶化。在这里,我们提出了一个新颖的自我监督框架,以检测低分辨率图像降解的对象。我们利用下采样降解作为一种自我监督信号的一种转换,以探索针对各种分辨率和其他退化条件的模棱两可的表示。自我设计(AERIS)框架中的自动编码分辨率可以进一步利用高级SR体系结构,并使用任意分辨率恢复解码器,以从退化的输入图像中重建原始对应关系。表示学习和对象检测均以端到端的培训方式共同优化。通用AERIS框架可以在具有不同骨架的各种主流对象检测架构上实现。广泛的实验表明,与现有方法相比,我们的方法在面对变化降解情况时取得了卓越的性能。代码将在https://github.com/cuiziteng/eccv_aeris上发布。
translated by 谷歌翻译
辐射场的最新进展可以使静态或动态3D场景的影照相渲染,但仍然不支持用于场景操纵或动画的显式变形。在本文中,我们提出了一种可以实现辐射场的新类型变形的方法:自由形式的辐射场磁场变形。我们使用一个三角形的网格,该网格封闭了称为笼子作为接口的前景对象,通过操纵笼顶点,我们的方法可以使辐射场的自由形式变形。我们方法的核心是基于笼子的变形,通常用于网格变形。我们提出了一种新颖的公式,以将其扩展到辐射场,该公式将采样点的位置和视图方向映射到从变形空间到规范空间,从而实现了变形场景的渲染。合成数据集和现实世界数据集的变形结果证明了我们方法的有效性。
translated by 谷歌翻译
我们为基于语义信息(称为ConceptBeam的语义信息)提出了一个新颖的框架。目标语音提取意味着在混合物中提取目标扬声器的语音。典型的方法一直在利用音频信号的性能,例如谐波结构和到达方向。相反,ConceptBeam通过语义线索解决了问题。具体来说,我们使用概念规范(例如图像或语音)提取说话者谈论概念的演讲,即感兴趣的主题。解决这个新颖的问题将为对话中讨论的特定主题等创新应用打开门。与关键字不同,概念是抽象的概念,使直接代表目标概念的挑战。在我们的方案中,通过将概念规范映射到共享的嵌入空间,将概念编码为语义嵌入。可以使用由图像及其口语字幕组成的配对数据进行深度度量学习来构建这种独立的空间。我们使用它来桥接模式依赖性信息,即混合物中的语音段以及指定的,无模式的概念。作为我们方案的证明,我们使用与口语标题相关的一组图像进行了实验。也就是说,我们从这些口语字幕中产生了语音混合物,并将图像或语音信号用作概念指定符。然后,我们使用已识别段的声学特征提取目标语音。我们将ConceptBeam与两种方法进行比较:一种基于从识别系统获得的关键字,另一个基于声音源分离。我们表明,概念束明显优于基线方法,并根据语义表示有效提取语音。
translated by 谷歌翻译