Salient object detection (SOD) aims to determine the most visually attractive objects in an image. With the development of virtual reality technology, 360{\deg} omnidirectional image has been widely used, but the SOD task in 360{\deg} omnidirectional image is seldom studied due to its severe distortions and complex scenes. In this paper, we propose a Multi-Projection Fusion and Refinement Network (MPFR-Net) to detect the salient objects in 360{\deg} omnidirectional image. Different from the existing methods, the equirectangular projection image and four corresponding cube-unfolding images are embedded into the network simultaneously as inputs, where the cube-unfolding images not only provide supplementary information for equirectangular projection image, but also ensure the object integrity of the cube-map projection. In order to make full use of these two projection modes, a Dynamic Weighting Fusion (DWF) module is designed to adaptively integrate the features of different projections in a complementary and dynamic manner from the perspective of inter and intra features. Furthermore, in order to fully explore the way of interaction between encoder and decoder features, a Filtration and Refinement (FR) module is designed to suppress the redundant information between the feature itself and the feature. Experimental results on two omnidirectional datasets demonstrate that the proposed approach outperforms the state-of-the-art methods both qualitatively and quantitatively.
translated by 谷歌翻译
网络体系结构搜索(NAS),尤其是可区分的体系结构搜索(DARTS)方法,已经显示出在特定感兴趣的特定数据集中学习出色的模型体系结构的强大力量。与使用固定的数据集相反,在这项工作中,我们关注NAS的不同但重要的方案:如何完善部署的网络模型体系结构,以增强其鲁棒性,并通过一些收集和错误分类的示例的指导来增强其鲁棒性,这些示例被某些降低了现实世界中的未知损坏具有特定的模式(例如噪声,模糊等)。为此,我们首先进行了一项实证研究,以验证模型体系结构绝对与腐败模式有关。令人惊讶的是,通过仅添加一些损坏和错误分类的示例(例如,$ 10^3 $示例)到清洁培训数据集(例如$ 5.0 \ times 10^4 $示例)中,我们可以完善模型体系结构并显着增强鲁棒性。为了使其更加实用,应仔细研究关键问题,即如何为有效的NAS指导选择适当的失败示例。然后,我们提出了一个新颖的核心失效指导飞镖,该飞镖嵌入了K-Center-Greedy算法的飞镖,以选择合适的损坏故障示例以完善模型体系结构。我们使用我们的方法在清洁和15个腐败上使用飞镖精制的DNN,并在四个特定的现实世界腐败的指导下进行了指导。与最先进的NAS以及基于数据启发的增强方法相比,我们的最终方法可以在损坏的数据集和原始清洁数据集上获得更高的精度。在某些腐败模式上,我们可以达到超过45%的绝对准确性提高。
translated by 谷歌翻译
随着网络技术的快速发展和网络设备的快速增长,数据吞吐量也大大增加。为了解决蜂窝网络中回程瓶颈的问题并满足人们对延迟的要求,基于预测的结果,网络体系结构等网络体系结构旨在主动将有限的流行内容保持在网络边缘。同时,内容(例如,深度神经网络模型,与Wikipedia类似知识库)和用户之间的相互作用可以视为动态二分图。在本文中,为了最大程度地提高缓存命中率,我们利用有效的动态图神经网络(DGNN)共同学习嵌入了两部分图中的结构和时间模式。此外,为了更深入地了解不断发展的图表中的动态,我们提出了一个基于信息时代(AOI)的注意机制,以提取有价值的历史信息,同时避免消息陈旧的问题。结合了上述预测模型,我们还开发了一种缓存选择算法,以根据预测结果做出缓存决策。广泛的结果表明,与两个现实世界数据集中的其他最先进的方案相比,我们的模型可以获得更高的预测准确性。命中率的结果进一步验证了基于我们提出的模型而不是其他传统方式的缓存政策的优势。
translated by 谷歌翻译
发现新材料是一项艰巨的挑战,对人类社会的进步至关重要。基于反复试验实验和计算模拟的常规方法是劳动密集型或昂贵的,取决于专家的启发式知识,成功的方式很大。最近,通过从已知材料数据集中学习隐式知识来生成材料的生成设计模型。但是,这些模型要么适用于特定的材料系统,要么由于其未能将物理规则纳入其模型训练过程而较低。在这里,我们提出了一种基于深度学习的物理学指导的晶体生成模型(PGCGM),以实现具有高结构多样性(多达20种不同空间组)的有效生成材料设计。我们模型的高性能表明了其捕获和利用晶体的对称约束和邻居原子之间的成对原子距离约束的能力。使用数据增强和空间原子聚类和合并,我们的PGCGM模型将整体生成有效性的性能提高了700 \%以上,与FTCP相比,FTCP是最先进的结构生成器之一,与45 \%相比,我们的整体生成有效性性能提高了。我们以前的立方体模型。新生成的晶体材料在原子空间分布和组成多样性方面也显示出更高的质量。我们通过密度功能理论(DFT)计算进一步验证了新的晶体结构。 2,000个中的1,869材料成功地优化了,其中39.6%的形成能量为阴性,5.3 \%的能量库船长小于0.25 eV/原子,表明它们的热力学稳定性和潜在的合成性。 1,869个晶体结构已沉积到卡罗来纳州材料数据库\ url {www.carolinamatdb.org}。
translated by 谷歌翻译
数据驱动的生成机器学习模型最近被出现为最有希望的新材料发现方法之一。虽然发电机型号可以产生数百万候选者,但训练快速准确的机器学习模型至关重要,以滤除具有所需特性的稳定,可合成的材料。然而,通过缺乏不稳定或不合益的样本严重阻碍了构建监督回归或分类筛查模型的努力,这通常不会收集和沉积在诸如ICSD和材料项目(MP)的材料数据库中。与此同时,这些数据库中有很多未标记的数据。在这里,我们提出了一个半监控的深度神经网络(TSDNN)模型,用于高性能形成能量和合成性预测,通过其独特的教师 - 学生双网络架构实现,并有效利用大量未标记数据。对于基于能量基于能量的稳定性筛选,与基线CGCNN回归模型相比,我们的半监控分类器实现了绝对的10.3 \%的准确性改进。对于合成性预测,我们的模型显着增加了基准PU学习从87.9 \%到97.9 \%的真正阳性率使用1/49型号参数。为了进一步证明我们模型的有效性,我们将我们的TSDNN-Energy和Tsdnn-InsteSizability模型与我们的Cubicgan发生器组合起来,以发现新型稳定的立方体结构。我们的模型中的1000个推荐的候选样品,其中512个具有由我们的DFT形成能量计算验证的负面形成能量。我们的实验结果表明,我们的半监督深度神经网络可以在大型生成材料设计中显着提高筛选准确性。
translated by 谷歌翻译
基于深度学习的生成模型,如DeepFake已经能够生成惊人的图像和视频。然而,当应用于产生晶体材料结构时,这些模型可能需要显着的变换,其中构建块,物理原子与像素非常不同。天然转移的生成模型倾向于产生不稳定或可合成的大部分物理上不可行的晶体结构。通过利用和添加物理导向的数据增强,丢失函数术语和后处理,我们的深度对抗网络(GAN)基于的生成模型现在可以生成具有更高物理可行性的晶体结构,并展开我们以前的型号,只能创建立方体结构。
translated by 谷歌翻译
在过去的几年里,深度神经网络(DNN)取得了巨大的成功,并且在许多应用领域中不断应用。然而,在工业任务的实际部署期间,由于超容易的原因,发现DNN被发现是错误的,缺乏在实际使用过程中对现实世界腐败的鲁棒性。为了解决这些挑战,通过通过在神经级别的再试,微调或直接重量固定来通过更新权重(即,网络参数)来修复实际操作环境下的近期尝试。在这项工作中,作为第一次尝试,我们通过共同优化架构和重量,以更高(即,块)级别来修复DNN。我们首先履行实证研究,以调查整个网络级和层次修复的限制,这激励我们探索块水平的DNN修复的新修复方向。为此,我们首先提出对弱势群体定位的对抗侵犯块定位的频谱分析,其在前向和后向过程中考虑块中的神经元“状态和权重”梯度,这使得即使在几个示例下也能够修复更准确的候选块定位。然后,我们进一步提出了面向架构的基于搜索的修复,该修复将目标块放宽到更高的深度特征级别的连续修复搜索空间。通过联合优化该空间中的架构和权重,我们可以识别更好的块架构。我们实施我们提出的修复技术作为一个名为ArchRepair的工具,并进行广泛的实验以验证提出的方法。结果表明,我们的方法不仅可以修复,还可以提高准确性和稳健性,优于最先进的DNN修复技术。
translated by 谷歌翻译
Scene text editing (STE) aims to replace text with the desired one while preserving background and styles of the original text. However, due to the complicated background textures and various text styles, existing methods fall short in generating clear and legible edited text images. In this study, we attribute the poor editing performance to two problems: 1) Implicit decoupling structure. Previous methods of editing the whole image have to learn different translation rules of background and text regions simultaneously. 2) Domain gap. Due to the lack of edited real scene text images, the network can only be well trained on synthetic pairs and performs poorly on real-world images. To handle the above problems, we propose a novel network by MOdifying Scene Text image at strokE Level (MOSTEL). Firstly, we generate stroke guidance maps to explicitly indicate regions to be edited. Different from the implicit one by directly modifying all the pixels at image level, such explicit instructions filter out the distractions from background and guide the network to focus on editing rules of text regions. Secondly, we propose a Semi-supervised Hybrid Learning to train the network with both labeled synthetic images and unpaired real scene text images. Thus, the STE model is adapted to real-world datasets distributions. Moreover, two new datasets (Tamper-Syn2k and Tamper-Scene) are proposed to fill the blank of public evaluation datasets. Extensive experiments demonstrate that our MOSTEL outperforms previous methods both qualitatively and quantitatively. Datasets and code will be available at https://github.com/qqqyd/MOSTEL.
translated by 谷歌翻译
Oxidation states are the charges of atoms after their ionic approximation of their bonds, which have been widely used in charge-neutrality verification, crystal structure determination, and reaction estimation. Currently only heuristic rules exist for guessing the oxidation states of a given compound with many exceptions. Recent work has developed machine learning models based on heuristic structural features for predicting the oxidation states of metal ions. However, composition based oxidation state prediction still remains elusive so far, which is more important in new material discovery for which the structures are not even available. This work proposes a novel deep learning based BERT transformer language model BERTOS for predicting the oxidation states of all elements of inorganic compounds given only their chemical composition. Our model achieves 96.82\% accuracy for all-element oxidation states prediction benchmarked on the cleaned ICSD dataset and achieves 97.61\% accuracy for oxide materials. We also demonstrate how it can be used to conduct large-scale screening of hypothetical material compositions for materials discovery.
translated by 谷歌翻译
Uncertainty quantification (UQ) has increasing importance in building robust high-performance and generalizable materials property prediction models. It can also be used in active learning to train better models by focusing on getting new training data from uncertain regions. There are several categories of UQ methods each considering different types of uncertainty sources. Here we conduct a comprehensive evaluation on the UQ methods for graph neural network based materials property prediction and evaluate how they truly reflect the uncertainty that we want in error bound estimation or active learning. Our experimental results over four crystal materials datasets (including formation energy, adsorption energy, total energy, and band gap properties) show that the popular ensemble methods for uncertainty estimation is NOT the best choice for UQ in materials property prediction. For the convenience of the community, all the source code and data sets can be accessed freely at \url{https://github.com/usccolumbia/materialsUQ}.
translated by 谷歌翻译