A diffusion model learns to predict a vector field of gradients. We propose to apply chain rule on the learned gradients, and back-propagate the score of a diffusion model through the Jacobian of a differentiable renderer, which we instantiate to be a voxel radiance field. This setup aggregates 2D scores at multiple camera viewpoints into a 3D score, and repurposes a pretrained 2D model for 3D data generation. We identify a technical challenge of distribution mismatch that arises in this application, and propose a novel estimation mechanism to resolve it. We run our algorithm on several off-the-shelf diffusion image generative models, including the recently released Stable Diffusion trained on the large-scale LAION dataset.
translated by 谷歌翻译
Automatically fixing software bugs is a challenging task. While recent work showed that natural language context is useful in guiding bug-fixing models, the approach required prompting developers to provide this context, which was simulated through commit messages written after the bug-fixing code changes were made. We instead propose using bug report discussions, which are available before the task is performed and are also naturally occurring, avoiding the need for any additional information from developers. For this, we augment standard bug-fixing datasets with bug report discussions. Using these newly compiled datasets, we demonstrate that various forms of natural language context derived from such discussions can aid bug-fixing, even leading to improved performance over using commit messages corresponding to the oracle bug-fixing commits.
translated by 谷歌翻译
球形图像处理已被广泛应用于许多重要领域,例如自动驾驶汽车,全球气候建模和医学成像的全向视觉。扩展针对平面图像开发的算法的算法是非平凡的。在这项工作中,我们专注于具有基于深度学习的正常化程序的球形图像的具有挑战性的任务。我们采用了快速的方向球形帧转换,而不是对平面图像的现有模型的幼稚应用,并基于framelet变换的稀疏性假设而开发了一种新颖的优化框架。此外,通过采用渐进式编码器架构,经过精心设计的新的,表现出色的CNN Denoiser,可以作为隐式正规化程序进行设计。最后,我们使用插件方法来处理提出的优化模型,可以通过训练CNN Denoiser先验来有效地实现。进行了数值实验,并表明所提出的算法可以极大地恢复损坏的球形图像,并使用深度学习的DeNoiser和Paint-&play模型实现最佳性能。
translated by 谷歌翻译
确定与医学实体相对应的医学文本中的跨度是许多医疗保健NLP任务的核心步骤之一,例如ICD编码,医学发现提取,医学注释上下文化等等。现有的实体提取方法依赖于医疗实体的固定词汇和有限的词汇,并且难以提取以不相交跨度为代表的实体。在本文中,我们提出了一种新的基于变压器的架构,称为OSLAT,OPEL SET LABEL COATION TRUSSSIONER,它解决了先前方法的许多局限性。我们的方法使用标签 - 注意机制来隐式学习与感兴趣的实体相关的跨度。这些实体可以作为自由文本提供,包括在OSLAT培训期间看不到的实体,即使它们是不相交的,该模型也可以提取跨度。为了测试我们方法的普遍性,我们在两个不同的数据集上训练两个单独的模型,这些数据集具有非常低的实体重叠:(1)来自HNLP的公共排放笔记数据集,以及(2)更具挑战性的专有患者文本数据集“原因”相遇”(RFE)。我们发现,应用于数据集上的OSLAT模型在应用于RFE数据集以及HNLP数据集的一部分时,在数据集上训练了基于规则和模糊字符串匹配基线,其中实体由分离跨度表示。我们的代码可以在https://github.com/curai/curai-research/tree/main/oslat上找到。
translated by 谷歌翻译
手工和小规模的黄金开采(ASGM)是许多家庭的重要收入来源,但它可以产生巨大的社会和环境影响,尤其是在发展中国家的雨林中。Sentinel-2卫星收集了多光谱图像,可用于检测水位和质量的变化,这表明采矿地点位置。这项工作着重于对秘鲁亚马逊雨林中ASGM活动的认可。我们根据支持向量机(SVM)测试了几个半监督分类器,以检测Madre de Dios地区从2019年到2021年的水体变化,这是ASGM活动的全球热点之一。实验表明,基于SVM的模型可以实现RGB的合理性能(使用Cohen的$ \ kappa $ 0.49)和6通道图像(使用Cohen的$ \ kappa $ 0.71),具有非常有限的注释。还分析了合并实验室色彩空间的功效。
translated by 谷歌翻译
点设置分类旨在建立一个表示学习模型,该模型区分点设置数据的空间和分类配置。此问题是在许多应用领域,如免疫学和微生物生态学的社会重要性。由于不同类别的点之间的相互作用并不总是平等,因此这个问题是具有挑战性的;结果,表示学习模型必须选择性地学习最相关的多分类关系。相关工程有限(1)学习不同多分类关系的重要性,特别是对于高阶相互作用,(2)并不完全利用超出只测量相对距离或应用前馈的点的空间分布神经网络坐标。为了克服这些限制,我们利用动态图形卷积神经网络(DGCNN)架构来设计新的多类别DGCNN(MC-DGCNN),为多分类点设置分类提供位置表示和点对注意层。 MC-DGCNN具有识别每个点对的分类重要性,并将其扩展到N-Way空间关系,同时仍然保留DGCNN(例如,差异性)的所有属性和益处。实验结果表明,该拟议的架构是在计算上有效的,显着优于现实世界数据集上的当前深度学习架构。
translated by 谷歌翻译
最近经过彻底调查了变压器多头自我关注机制。一方面,研究人员对理解为什么以及变压器如何工作。另一方面,他们提出了新的注意增强方法,使变压器更准确,高效和可解释。在本文中,我们在循环管道中协同促使这两条研究线,首先找到了重要的任务特定的注意模式。然后应用那些模式,不仅应用于原始模型,还应用于较小的模型,作为人类引导的知识蒸馏过程。在提取摘要任务的情况下,在案例研究中对我们的管道的好处。在受欢迎的Bertsum模型中找到三种有意义的关注模式之后,实验表明,当我们注入这种模式时,原始和较小模型都显示出性能的改进,并且可以说是可争议的解释性。
translated by 谷歌翻译
Objective: Traumatic brain injury can be caused by head impacts, but many brain injury risk estimation models are not equally accurate across the variety of impacts that patients may undergo and the characteristics of different types of impacts are not well studied. We investigated the spectral characteristics of different head impact types with kinematics classification. Methods: Data was analyzed from 3,262 head impacts from lab reconstruction, American football, mixed martial arts, and publicly available car crash data. A random forest classifier with spectral densities of linear acceleration and angular velocity was built to classify head impact types (e.g., football, car crash, mixed martial arts). To test the classifier robustness, another 271 lab-reconstructed impacts were obtained from 5 other instrumented mouthguards. Finally, with the classifier, type-specific, nearest-neighbor regression models were built for brain strain. Results: The classifier reached a median accuracy of 96% over 1,000 random partitions of training and test sets. The most important features in the classification included both low-frequency and high-frequency features, both linear acceleration features and angular velocity features. Different head impact types had different distributions of spectral densities in low-frequency and high-frequency ranges (e.g., the spectral densities of MMA impacts were higher in high-frequency range than in the low-frequency range). The type-specific regression showed a generally higher R^2-value than baseline models without classification. Conclusion: The machine-learning-based classifier enables a better understanding of the impact kinematics spectral density in different sports, and it can be applied to evaluate the quality of impact-simulation systems and on-field data augmentation.
translated by 谷歌翻译
随着对深神经网络(DNN)模型的越来越关注,对于此类模型,攻击也即将发生。例如,攻击者可以以特定方式仔细构建图像(也称为对抗性示例),以误导DNN模型以输出不正确的分类结果。同样,提出了许多努力来检测和减轻对抗性例子,通常是针对某些专门的攻击。在本文中,我们提出了一种基于数字水印的新型方法,以生成图像对抗性示例以愚弄DNN模型。具体而言,Watermark图像的部分主要特征几乎被视而不见地嵌入到主机图像中,旨在篡改和损坏DNN模型的识别能力。我们设计了一种有效的机制来选择主机图像和水印图像,并利用改进的离散小波变换(DWT)的拼布水印算法,并使用一组有效的超参数将数字水印从水印图像数据集嵌入到原始图像中,以生成图像对抗性示例。实验结果表明,对COFAR-10数据集的攻击成功率平均达到95.47%,最高为98.71%。此外,我们的方案能够有效地生成大量的对抗示例,具体地,平均完成了1.17秒,以完成CIFAR-10数据集上每个图像的攻击。此外,我们设计了一个基线实验,它使用高斯噪声作为水印图像数据集生成的水印图像,该数据集也显示了我们方案的有效性。同样,我们还提出了基于修改的离散余弦变换(DCT)的拼布水印算法。为了确保可重复性和可重复性,可以在GitHub上获得源代码。
translated by 谷歌翻译
Unsupervised learning with generative adversarial networks (GANs) has proven hugely successful. Regular GANs hypothesize the discriminator as a classifier with the sigmoid cross entropy loss function. However, we found that this loss function may lead to the vanishing gradients problem during the learning process. To overcome such a problem, we propose in this paper the Least Squares Generative Adversarial Networks (LS-GANs) which adopt the least squares loss function for the discriminator. We show that minimizing the objective function of LSGAN yields minimizing the Pearson χ 2 divergence. There are two benefits of LSGANs over regular GANs. First, LSGANs are able to generate higher quality images than regular GANs. Second, LSGANs perform more stable during the learning process. We evaluate LSGANs on five scene datasets and the experimental results show that the images generated by LSGANs are of better quality than the ones generated by regular GANs. We also conduct two comparison experiments between LSGANs and regular GANs to illustrate the stability of LSGANs.
translated by 谷歌翻译