在训练阶段通常使用辍学作为正则化方法,并用于量化深度学习的不确定性。我们建议在培训期间使用辍学以及推理步骤,以及平均多种预测,以提高准确性,同时减少和量化不确定性。评估结果对仅3方向扫描获得的分数各向异性(FA)和平均扩散率(MD)映射。通过我们的方法,与无丢失的网络输出相比,可以显着提高准确性,特别是当训练数据集很小时。此外,产生置信度图,这可能有助于诊断看不见的病理学或伪影。
translated by 谷歌翻译
扩散加权图像(DWIS)中的噪声降低了扩散张量磁共振成像(DTI)导出的微结构参数的准确性和精度,并导致延长的采集时间来实现改进的信噪比(SNR)。基于深度学习的图像去噪使用卷积神经网络(CNNS)具有卓越的性能,但通常需要额外的高SNR数据来监督CNN的培训,这降低了实际可行性。我们开发了一个自我监督的深度学习的方法,标题为“SDNDTI”,用于去噪DTI数据,这不需要额外的高SNR数据进行培训。具体地,SDNDTI将多向DTI数据划分为许多子集,每个子​​集中沿着沿着最佳选择的扩散编码方向组成的六个DWI卷,该编码方向是对张力配件的稳健,然后沿着拟合的扩散张量沿所有获取的方向合成DWI体积使用数据的每个子集作为CNN的输入数据。另一方面,SDNDTI沿着使用所有获取的数据作为训练目标的扩散张量,沿着获取的扩散编码方向合成DWI卷。 SDNDTI使用深3维CNN从合成的DWI卷中的每个子集中消除噪声,以匹配清洁器目标DWI卷的质量,通过平均所有去噪数据的所有子集实现更高的SNR。 SDNDTI的去噪功效在于人类连接项目(HCP)提供的两种数据集和衰老中的寿命HCP。 SDNDTI结果保留了图像清晰度和纹理细节,并大大改善了原始数据的影响。 SDNDTI的结果与来自最先进的传统去噪算法包括BM4D,AONLM和MPPCA的常规去噪算法的结果相当。
translated by 谷歌翻译
推理是计算机的基本问题,并且在人工智能中深入研究。在本文中,我们专门针对回答知识图(KGS)的多跳逻辑查询。这是一项复杂的任务,因为在实际情况下,图形往往很大且不完整。以前的大多数作品都无法创建模型,这些模型接受了完整的一阶逻辑(fol)查询,其中包括负查询,并且只能处理有限的查询结构集。此外,大多数方法都呈现只能执行其制作的逻辑操作的逻辑运算符。我们介绍了一组模型,这些模型使用神经网络来创建单点矢量嵌入以回答查询。神经网络的多功能性允许该框架处理连词($ \ wedge $),脱节($ \ vee $)和否定($ \ neg $)运算符的框架查询。我们通过对众所周知的基准数据集进行了广泛的实验,通过实验证明了模型的性能。除了拥有更多多功能运营商外,模型还获得了10 \%的相对增加,而基于单点矢量嵌入的最佳性能状态和比原始方法的相对增加了30 \%。
translated by 谷歌翻译
科学出版物的产出成倍增长。因此,跟踪趋势和变化越来越具有挑战性。了解科学文档是下游任务的重要一步,例如知识图构建,文本挖掘和纪律分类。在这个研讨会中,我们从科学出版物的摘要中可以更好地理解关键字和键形酶提取。
translated by 谷歌翻译
检测欺诈性交易是控制​​电子商务市场风险的重要组成部分。除了已经在生产中部署的基于规则和机器学习过滤器外,我们还希望使用图形神经网络(GNN)进行有效的实时推理,这对于在事务图中捕获多跃风风险传播非常有用。但是,在生产中实施GNN时出现了两个挑战。首先,在消息传递中不应考虑以预测过去中的动态图中的未来信息。其次,图形查询和GNN模型推断的延迟通常高达数百毫秒,这对于某些关键的在线服务来说是昂贵的。为了应对这些挑战,我们提出了一个批处理和实时的成立图拓扑(BRIGHT)框架,以进行端到端的GNN学习,以允许有效的在线实时推理。 Bright框架由图形转换模块(两阶段有向图)和相应的GNN体系结构(Lambda神经网络)组成。两阶段的指示图保证了通过邻居传递的信息仅来自历史支付交易。它分别由代表历史关系和实时链接的两个子图组成。 Lambda神经网络将推断分为两个阶段:实体嵌入的批次推断和交易预测的实时推断。我们的实验表明,在平均W.R.T.〜精确度中,BRIGHT优于基线模型> 2 \%。此外,BRIGHT在实时欺诈检测上在计算上是有效的。关于端到端性能(包括邻居查询和推理),BRIGHT可以将P99延迟降低> 75 \%。对于推理阶段,与传统GNN相比,我们的加速平均为7.8美元。
translated by 谷歌翻译
表是存储数据的永远存在的结构。现在存在不同的方法来物理地存储表格数据。PDF,图像,电子表格和CSV是领先的例子。能够解析由这些结构界限的表结构和提取内容在许多应用中具有很高的重要性。在本文中,我们设计了Diallagarser,一个系统能够在天然PDF和具有高精度的扫描图像中解析表的系统。我们已经进行了广泛的实验,以展示领域适应在开发这种工具方面的功效。此外,我们创建了TableAnnotator和Excelannotator,构成了基于电子表格的弱监督机制和管道,以实现表解析。我们与研究界共享这些资源,以促进这种有趣方向的进一步研究。
translated by 谷歌翻译
在线零售平台,积极检测交易风险至关重要,以提高客户体验,并尽量减少财务损失。在这项工作中,我们提出了一种可解释的欺诈行为预测框架,主要由探测器和解释器组成。 Xfraud探测器可以有效和有效地预测进货交易的合法性。具体地,它利用异构图形神经网络来从事务日志中的信息的非渗透键入实体中学习表达式表示。 Xfraud中的解释器可以从图表中生成有意义和人性化的解释,以便于业务部门中的进一步进程。在我们对具有高达11亿节点和37亿边缘的实际交易网络上的Xfraud实验中,XFraud能够在许多评估度量中倾销各种基线模型,同时在分布式设置中剩余可扩展。此外,我们表明,XFraud解释者可以通过定量和定性评估来显着帮助业务分析来产生合理的解释。
translated by 谷歌翻译
This paper focuses on designing efficient models with low parameters and FLOPs for dense predictions. Even though CNN-based lightweight methods have achieved stunning results after years of research, trading-off model accuracy and constrained resources still need further improvements. This work rethinks the essential unity of efficient Inverted Residual Block in MobileNetv2 and effective Transformer in ViT, inductively abstracting a general concept of Meta-Mobile Block, and we argue that the specific instantiation is very important to model performance though sharing the same framework. Motivated by this phenomenon, we deduce a simple yet efficient modern \textbf{I}nverted \textbf{R}esidual \textbf{M}obile \textbf{B}lock (iRMB) for mobile applications, which absorbs CNN-like efficiency to model short-distance dependency and Transformer-like dynamic modeling capability to learn long-distance interactions. Furthermore, we design a ResNet-like 4-phase \textbf{E}fficient \textbf{MO}del (EMO) based only on a series of iRMBs for dense applications. Massive experiments on ImageNet-1K, COCO2017, and ADE20K benchmarks demonstrate the superiority of our EMO over state-of-the-art methods, \eg, our EMO-1M/2M/5M achieve 71.5, 75.1, and 78.4 Top-1 that surpass \textbf{SoTA} CNN-/Transformer-based models, while trading-off the model accuracy and efficiency well.
translated by 谷歌翻译
Supervised Question Answering systems (QA systems) rely on domain-specific human-labeled data for training. Unsupervised QA systems generate their own question-answer training pairs, typically using secondary knowledge sources to achieve this outcome. Our approach (called PIE-QG) uses Open Information Extraction (OpenIE) to generate synthetic training questions from paraphrased passages and uses the question-answer pairs as training data for a language model for a state-of-the-art QA system based on BERT. Triples in the form of <subject, predicate, object> are extracted from each passage, and questions are formed with subjects (or objects) and predicates while objects (or subjects) are considered as answers. Experimenting on five extractive QA datasets demonstrates that our technique achieves on-par performance with existing state-of-the-art QA systems with the benefit of being trained on an order of magnitude fewer documents and without any recourse to external reference data sources.
translated by 谷歌翻译
Transformer has achieved impressive successes for various computer vision tasks. However, most of existing studies require to pretrain the Transformer backbone on a large-scale labeled dataset (e.g., ImageNet) for achieving satisfactory performance, which is usually unavailable for medical images. Additionally, due to the gap between medical and natural images, the improvement generated by the ImageNet pretrained weights significantly degrades while transferring the weights to medical image processing tasks. In this paper, we propose Bootstrap Own Latent of Transformer (BOLT), a self-supervised learning approach specifically for medical image classification with the Transformer backbone. Our BOLT consists of two networks, namely online and target branches, for self-supervised representation learning. Concretely, the online network is trained to predict the target network representation of the same patch embedding tokens with a different perturbation. To maximally excavate the impact of Transformer from limited medical data, we propose an auxiliary difficulty ranking task. The Transformer is enforced to identify which branch (i.e., online/target) is processing the more difficult perturbed tokens. Overall, the Transformer endeavours itself to distill the transformation-invariant features from the perturbed tokens to simultaneously achieve difficulty measurement and maintain the consistency of self-supervised representations. The proposed BOLT is evaluated on three medical image processing tasks, i.e., skin lesion classification, knee fatigue fracture grading and diabetic retinopathy grading. The experimental results validate the superiority of our BOLT for medical image classification, compared to ImageNet pretrained weights and state-of-the-art self-supervised learning approaches.
translated by 谷歌翻译