磁共振成像(MRI)是中风成像的中心方式。它被用来接受患者的治疗决定,例如选择患者进行静脉溶栓或血管内治疗。随后在住院期间使用MRI来通过可视化梗塞核心大小和位置来预测结果。此外,它可以用来表征中风病因,例如(心脏) - 栓塞和非胚胎中风之间的区分。基于计算机的自动医疗图像处理越来越多地进入临床常规。缺血性中风病变分割(ISLE)挑战的先前迭代有助于生成鉴定急性和急性缺血性中风病变分割的基准方法。在这里,我们介绍了一个专家注册的多中心MRI数据集,以分割急性到亚急性中风病变。该数据集包括400个多供应商MRI案例,中风病变大小,数量和位置的可变性很高。它分为n = 250的训练数据集和n = 150的测试数据集。所有培训数据将公开可用。测试数据集将仅用于模型验证,并且不会向公众发布。该数据集是Isles 2022挑战的基础,目的是找到算法方法,以实现缺血性中风的稳健和准确分割算法的开发和基准测试。
translated by 谷歌翻译
Creating compelling captions for data visualizations has been a longstanding challenge. Visualization researchers are typically untrained in journalistic reporting and hence the captions that are placed below data visualizations tend to be not overly engaging and rather just stick to basic observations about the data. In this work we explore the opportunities offered by the newly emerging crop of large language models (LLM) which use sophisticated deep learning technology to produce human-like prose. We ask, can these powerful software devices be purposed to produce engaging captions for generic data visualizations like a scatterplot. It turns out that the key challenge lies in designing the most effective prompt for the LLM, a task called prompt engineering. We report on first experiments using the popular LLM GPT-3 and deliver some promising results.
translated by 谷歌翻译
Recent advances in generative adversarial networks (GANs) have demonstrated the capabilities of generating stunning photo-realistic portrait images. While some prior works have applied such image GANs to unconditional 2D portrait video generation and static 3D portrait synthesis, there are few works successfully extending GANs for generating 3D-aware portrait videos. In this work, we propose PV3D, the first generative framework that can synthesize multi-view consistent portrait videos. Specifically, our method extends the recent static 3D-aware image GAN to the video domain by generalizing the 3D implicit neural representation to model the spatio-temporal space. To introduce motion dynamics to the generation process, we develop a motion generator by stacking multiple motion layers to generate motion features via modulated convolution. To alleviate motion ambiguities caused by camera/human motions, we propose a simple yet effective camera condition strategy for PV3D, enabling both temporal and multi-view consistent video generation. Moreover, PV3D introduces two discriminators for regularizing the spatial and temporal domains to ensure the plausibility of the generated portrait videos. These elaborated designs enable PV3D to generate 3D-aware motion-plausible portrait videos with high-quality appearance and geometry, significantly outperforming prior works. As a result, PV3D is able to support many downstream applications such as animating static portraits and view-consistent video motion editing. Code and models will be released at https://showlab.github.io/pv3d.
translated by 谷歌翻译
数十年来,计算机系统持有大量个人数据。一方面,这种数据丰度允许在人工智能(AI),尤其是机器学习(ML)模型中突破。另一方面,它可能威胁用户的隐私并削弱人类与人工智能之间的信任。最近的法规要求,可以从一般情况下从计算机系统中删除有关用户的私人信息,特别是根据要求从ML模型中删除(例如,“被遗忘的权利”)。虽然从后端数据库中删除数据应该很简单,但在AI上下文中,它不够,因为ML模型经常“记住”旧数据。现有的对抗攻击证明,我们可以从训练有素的模型中学习私人会员或培训数据的属性。这种现象要求采用新的范式,即机器学习,以使ML模型忘记了特定的数据。事实证明,由于缺乏共同的框架和资源,最近在机器上学习的工作无法完全解决问题。在本调查文件中,我们试图在其定义,场景,机制和应用中对机器进行彻底的研究。具体而言,作为最先进的研究的类别集合,我们希望为那些寻求机器未学习的入门及其各种表述,设计要求,删除请求,算法和用途的人提供广泛的参考。 ML申请。此外,我们希望概述范式中的关键发现和趋势,并突出显示尚未看到机器无法使用的新研究领域,但仍可以受益匪浅。我们希望这项调查为ML研究人员以及寻求创新隐私技术的研究人员提供宝贵的参考。我们的资源是在https://github.com/tamlhp/awesome-machine-unlearning上。
translated by 谷歌翻译
将差异化随机梯度下降(DPSGD)应用于培训现代大规模神经网络(例如基于变压器的模型)是一项艰巨的任务,因为在每个迭代尺度上添加了噪声的幅度,都具有模型维度,从而阻碍了学习能力显著地。我们提出了一个统一的框架,即$ \ textsf {lsg} $,该框架充分利用了神经网络的低级别和稀疏结构,以减少梯度更新的维度,从而减轻DPSGD的负面影响。首先使用一对低级矩阵近似梯度更新。然后,一种新颖的策略用于稀疏梯度,从而导致低维,较少的嘈杂更新,这些更新尚未保留神经网络的性能。关于自然语言处理和计算机视觉任务的经验评估表明,我们的方法的表现优于其他最先进的基线。
translated by 谷歌翻译
我们在差异隐私(DP)的洗牌模型中研究高斯机制。特别是,我们表征了该机制的r \'enyi差异隐私(RDP),表明它是形式:$$ \ epsilon(\ lambda)\ leq \ leq \ frac {1} {\ lambda-rambda-1} \ log \ left( \ frac { } \ binom {\ lambda!} {k_1,\ dotsc,k_n} e^{\ sum_ {\ sum_ {i = 1}^nk_i^2/2 \ sigma^2} \ right)由高斯RDP限制在上面,而不会改组。混乱的高斯RDP在组成多种DP机制方面是有利的,在该机制中,我们证明了其对散装模型的隐私保证的最新近似DP组成定理的改进。此外,我们将研究扩展到了次采样的洗牌机制和最近提出的洗牌机制,这些机制是针对分布式/联合学习的协议。最后,对这些机制进行了一项实证研究,以证明在分布式学习框架下采用洗牌高斯机制来保证严格的用户隐私的功效。
translated by 谷歌翻译
最近对具有正式隐私保证的分布式计算的研究,例如联合学习的差异私有(DP),利用每回合中客户的随机抽样(通过亚采样进行的隐私放大)来达到令人满意的隐私水平。然而,实现这一目标需要强大的假设,这些假设可能无法实践,包括对客户的精确和统一的亚采样,以及高度信任的聚合器来处理客户的数据。在本文中,我们探讨了一个更实用的协议,改组了办理登机手续,以解决上述问题。该协议依靠客户端做出独立和随机的决定来参与计算,释放服务器发射的亚采样要求,并启用客户端辍学的强大建模。此外,采用了称为洗牌模型的较弱的信任模型,而不是使用受信任的聚合器。为此,我们介绍了新工具来表征洗牌的r \'enyi差异隐私(RDP)。我们表明,我们的新技术在隐私保证中至少提高了三次,而在各种参数制度下使用近似DP的强大组成的人进行了三倍。此外,我们提供了一种数值方法来跟踪通用洗牌机构的隐私,包括具有高斯机制的分布式随机梯度下降(SGD)。据我们所知,这也是文献中分布式设置下本地/洗牌模型中高斯机制的首次评估,这可能具有独立的兴趣。
translated by 谷歌翻译
Recent state-of-the-art one-stage instance segmentation model SOLO divides the input image into a grid and directly predicts per grid cell object masks with fully-convolutional networks, yielding comparably good performance as traditional two-stage Mask R-CNN yet enjoying much simpler architecture and higher efficiency. We observe SOLO generates similar masks for an object at nearby grid cells, and these neighboring predictions can complement each other as some may better segment certain object part, most of which are however directly discarded by non-maximum-suppression. Motivated by the observed gap, we develop a novel learning-based aggregation method that improves upon SOLO by leveraging the rich neighboring information while maintaining the architectural efficiency. The resulting model is named SODAR. Unlike the original per grid cell object masks, SODAR is implicitly supervised to learn mask representations that encode geometric structure of nearby objects and complement adjacent representations with context. The aggregation method further includes two novel designs: 1) a mask interpolation mechanism that enables the model to generate much fewer mask representations by sharing neighboring representations among nearby grid cells, and thus saves computation and memory; 2) a deformable neighbour sampling mechanism that allows the model to adaptively adjust neighbor sampling locations thus gathering mask representations with more relevant context and achieving higher performance. SODAR significantly improves the instance segmentation performance, e.g., it outperforms a SOLO model with ResNet-101 backbone by 2.2 AP on COCO \texttt{test} set, with only about 3\% additional computation. We further show consistent performance gain with the SOLOv2 model.
translated by 谷歌翻译
深度神经网络(DNN)具有嘈杂的权重,我们将其称为嘈杂的神经网络(Noisynns),从DNN的存在下存在噪声的训练和推理。 Noisynns在许多新应用中出现,包括DNN的无线传输,模拟设备中的DNN的有效部署或存储,以及DNN权重的截断或量化。本文研究了Noisynns的根本问题:如何从嘈杂的表现形式重建DNN重量。虽然所有先前的作品都依赖于最大可能性(ML)估计,但本文提出了一种去噪方法来重建DNN,目的是最大化重建模型的推理准确性。我们的脱氮机的优越性在两个小规模问题中经过严格经过严格地证明,其中我们考虑了二次神经网络功能和浅前馈神经网络。当应用于具有现代DNN架构的高级学习任务时,我们的Denoiser表现出比ML估算器的性能显着更好。考虑去噪DNN模型的平均测试准确性与噪声功率比(WNR)性能的重量方差。当去噪产生从嘈杂推理引起的嘈杂的BERT模型时,我们的脱氮机以1.1 dB的估计优于ML估计,以获得75%的测试精度。当去噪产生从嘈杂训练产生的嘈杂reset18模型时,我们的丹机优于13.4 dB和8.3 dB的ML估计,以分别实现60%和80%的测试精度。
translated by 谷歌翻译
在2015年和2019年之间,地平线的成员2020年资助的创新培训网络名为“Amva4newphysics”,研究了高能量物理问题的先进多变量分析方法和统计学习工具的定制和应用,并开发了完全新的。其中许多方法已成功地用于提高Cern大型Hadron撞机的地图集和CMS实验所执行的数据分析的敏感性;其他几个人,仍然在测试阶段,承诺进一步提高基本物理参数测量的精确度以及新现象的搜索范围。在本文中,在研究和开发的那些中,最相关的新工具以及对其性能的评估。
translated by 谷歌翻译