Deep Metric Learning (DML) learns a non-linear semantic embedding from input data that brings similar pairs together while keeping dissimilar data away from each other. To this end, many different methods are proposed in the last decade with promising results in various applications. The success of a DML algorithm greatly depends on its loss function. However, no loss function is perfect, and it deals only with some aspects of an optimal similarity embedding. Besides, the generalizability of the DML on unseen categories during the test stage is an important matter that is not considered by existing loss functions. To address these challenges, we propose novel approaches to combine different losses built on top of a shared deep feature extractor. The proposed ensemble of losses enforces the deep model to extract features that are consistent with all losses. Since the selected losses are diverse and each emphasizes different aspects of an optimal semantic embedding, our effective combining methods yield a considerable improvement over any individual loss and generalize well on unseen categories. Here, there is no limitation in choosing loss functions, and our methods can work with any set of existing ones. Besides, they can optimize each loss function as well as its weight in an end-to-end paradigm with no need to adjust any hyper-parameter. We evaluate our methods on some popular datasets from the machine vision domain in conventional Zero-Shot-Learning (ZSL) settings. The results are very encouraging and show that our methods outperform all baseline losses by a large margin in all datasets.
translated by 谷歌翻译
群的行为来自代理的局部互动及其环境通常被编码为简单规则。通过观看整体群体行为的视频来提取规则可以帮助我们研究和控制自然界的群体行为,或者是由外部演员设计的人造群体。它还可以作为群体机器人技术灵感的新来源。然而,提取此类规则是具有挑战性的,因为群体的新兴特性与其当地互动之间通常没有明显的联系。为此,我们开发了一种方法,可以自动从视频演示中提取可理解的群体控制器。该方法使用由比较八个高级群指标的健身函数驱动的进化算法。该方法能够在简单的集体运动任务中提取许多控制器(行为树)。然后,我们对导致不同树木但类似行为的行为进行定性分析。这提供了基于观察值自动提取群体控制器的第一步。
translated by 谷歌翻译
能量分解估计的单仪表逐一逐个电能量,以衡量整个房屋的电力需求。与侵入性负载监测相比,尼尔姆(非侵入性负载监控)是低成本,易于部署和灵活的。在本文中,我们提出了一种新方法,即创建的IMG-NILM,该方法利用卷积神经网络(CNN)来分解表示为图像的电力数据。事实证明,CNN具有图像有效,因此,将数据作为时间序列而不是传统的电力表示,而是将其转换为热图,而较高的电读数则被描绘成“更热”的颜色。然后在CNN中使用图像表示来检测来自聚合数据的设备的签名。 IMG-NILM是灵活的,在分解各种类型的设备方面表现出一致的性能;包括单个和多个状态。它在单个房屋内的英国戴尔数据集中达到了高达93%的测试准确性,那里有大量设备。在从不同房屋中收集电力数据的更具挑战性的环境中,IMG-NILM的平均准确度也非常好,为85%。
translated by 谷歌翻译
深度学习和转移学习的进步为农业的各种自动化分类任务铺平了道路,包括植物疾病,害虫,杂草和植物物种检测。然而,农业自动化仍然面临各种挑战,例如数据集的大小和缺乏植物域特异性预处理模型。特定于域的预处理模型显示了各种计算机视觉任务的最先进的表现,包括面部识别和医学成像诊断。在本文中,我们提出了Agrinet数据集,该数据集是来自19个地理位置的160k农业图像的集合,几个图像标题为设备,以及423种以上的植物物种和疾病。我们还介绍了Agrinet模型,这是一组预处理的模型:VGG16,VGG19,Inception-V3,InceptionResnet-V2和Xception。 Agrinet-VGG19的分类准确性最高的94%,最高的F1分数为92%。此外,发现所有提出的模型都可以准确地对423种植物物种,疾病,害虫和杂草分类,而Inception-V3模型的精度最低为87%。与ImageNet相比,实验以评估Agrinet模型优势的实验在两个外部数据集上进行了模型:来自孟加拉国的害虫和植物疾病数据集和来自克什米尔的植物疾病数据集。
translated by 谷歌翻译