图表信号处理是一种普遍存在的任务,如传感器,社会,运输和大脑网络,点云处理和图形神经网络等许多应用程序。通常,图形信号在感测过程中损坏,从而需要恢复。在本文中,我们提出了一种基于深度算法展开(DAU)的图形信号恢复方法。首先,我们通过展开乘法器(ADMM)的交替方向方法的迭代来呈现曲线图信号置位。然后,我们建议通过展开即插即用ADMM(PNP-ADMM)的迭代进行线性劣化的一般恢复方法。在第二种方法中,将展开的基于ADMM的Denoiser纳入子模块,导致嵌套的DAU结构。所提出的去噪/恢复方法中的参数以端到端的方式进行培训。我们的方法是可解释的,并保持参数的数量,因为我们只调谐与图形的正则化参数。我们克服了现有曲线图信号恢复方法中的两个主要挑战:1)由于固定参数,凸优化算法的有限性能由于通常手动确定的固定参数。 2)图形神经网络的大量参数导致训练难度。对曲线信号去噪和插值的几个实验是对合成和真实世界的数据进行的。所提出的方法在两个任务中的根均方误差方面,在几种现有技术上显示了性能改进。
translated by 谷歌翻译
我们提出了一种基于语境化嵌入的单词和实体的全局实体消除歧义(ED)模型。我们的模型基于BERT和培训我们的新培训任务,使模型能够捕获基于Word的本地和基于实体的全局上下文信息。该模型解决了ED作为序列决策任务,有效地使用两种类型的上下文信息。我们在五个标准ED数据集中实现了新的最先进结果:AIDA-CONLL,MSNBC,AQUAINT,ACE2004和WNED-Wiki。我们的源代码和培训的模型检查点可在https://github.com/studio-ousia/luke获得。
translated by 谷歌翻译
Large-scale vision-language models such as CLIP have shown impressive performance on zero-shot image classification and image-to-text retrieval. However, such zero-shot performance of CLIP-based models does not realize in tasks that require a finer-grained correspondence between vision and language, such as Visual Question Answering (VQA). We investigate why this is the case, and report an interesting phenomenon of CLIP, which we call the Concept Association Bias (CAB), as a potential cause of the difficulty of applying CLIP to VQA and similar tasks. CAB is especially apparent when two concepts are present in the given image while a text prompt only contains a single concept. In such a case, we find that CLIP tends to treat input as a bag of concepts and attempts to fill in the other missing concept crossmodally, leading to an unexpected zero-shot prediction. For example, when asked for the color of a lemon in an image, CLIP predicts ``purple'' if the image contains a lemon and an eggplant. We demonstrate the Concept Association Bias of CLIP by showing that CLIP's zero-shot classification performance greatly suffers when there is a strong concept association between an object (e.g. lemon) and an attribute (e.g. its color). On the other hand, when the association between object and attribute is weak, we do not see this phenomenon. Furthermore, we show that CAB is significantly mitigated when we enable CLIP to learn deeper structure across image and text embeddings by adding an additional Transformer on top of CLIP and fine-tuning it on VQA. We find that across such fine-tuned variants of CLIP, the strength of CAB in a model predicts how well it performs on VQA.
translated by 谷歌翻译
A practical issue of edge AI systems is that data distributions of trained dataset and deployed environment may differ due to noise and environmental changes over time. Such a phenomenon is known as a concept drift, and this gap degrades the performance of edge AI systems and may introduce system failures. To address this gap, a retraining of neural network models triggered by concept drift detection is a practical approach. However, since available compute resources are strictly limited in edge devices, in this paper we propose a lightweight concept drift detection method in cooperation with a recently proposed on-device learning technique of neural networks. In this case, both the neural network retraining and the proposed concept drift detection are done by sequential computation only to reduce computation cost and memory utilization. Evaluation results of the proposed approach shows that while the accuracy is decreased by 3.8%-4.3% compared to existing batch-based detection methods, it decreases the memory size by 88.9%-96.4% and the execution time by 1.3%-83.8%. As a result, the combination of the neural network retraining and the proposed concept drift detection method is demonstrated on Raspberry Pi Pico that has 264kB memory.
translated by 谷歌翻译
We propose RANA, a relightable and articulated neural avatar for the photorealistic synthesis of humans under arbitrary viewpoints, body poses, and lighting. We only require a short video clip of the person to create the avatar and assume no knowledge about the lighting environment. We present a novel framework to model humans while disentangling their geometry, texture, and also lighting environment from monocular RGB videos. To simplify this otherwise ill-posed task we first estimate the coarse geometry and texture of the person via SMPL+D model fitting and then learn an articulated neural representation for photorealistic image generation. RANA first generates the normal and albedo maps of the person in any given target body pose and then uses spherical harmonics lighting to generate the shaded image in the target lighting environment. We also propose to pretrain RANA using synthetic images and demonstrate that it leads to better disentanglement between geometry and texture while also improving robustness to novel body poses. Finally, we also present a new photorealistic synthetic dataset, Relighting Humans, to quantitatively evaluate the performance of the proposed approach.
translated by 谷歌翻译
鉴于一个人的肖像图像和目标照明的环境图,肖像重新旨在重新刷新图像中的人,就好像该人出现在具有目标照明的环境中一样。为了获得高质量的结果,最近的方法依靠深度学习。一种有效的方法是用高保真输入输出对的高保真数据集监督对深神经网络的培训,并以光阶段捕获。但是,获取此类数据需要昂贵的特殊捕获钻机和耗时的工作,从而限制了对少数机智的实验室的访问。为了解决限制,我们提出了一种新方法,该方法可以与最新的(SOTA)重新确定方法相提并论,而无需光阶段。我们的方法基于这样的意识到,肖像图像的成功重新重新取决于两个条件。首先,该方法需要模仿基于物理的重新考虑的行为。其次,输出必须是逼真的。为了满足第一个条件,我们建议通过通过虚拟光阶段生成的训练数据来训练重新网络,该培训数据在不同的环境图下对各种3D合成人体进行了基于物理的渲染。为了满足第二种条件,我们开发了一种新型的合成对真实方法,以将光真实主义带入重新定向网络输出。除了获得SOTA结果外,我们的方法还提供了与先前方法相比的几个优点,包括可控的眼镜和更暂时的结果以重新欣赏视频。
translated by 谷歌翻译
尽管卷积神经网络(CNN)在图像识别方面具有很高的精度,但它们容易受到对抗性示例和分布数据的影响,并且已经指出了人类识别的差异。为了提高针对分布数据的鲁棒性,我们提出了一种基于频率的数据增强技术,该技术将频率组件用同一类的其他图像替换。当培训数据为CIFAR10并且分发数据的数据为SVHN时,使用该方法训练的模型的接收器操作特征(AUROC)曲线从89.22 \%\%增加到98.15 \%,并进一步增加到98.59\%与另一种数据增强方法结合使用。此外,我们在实验上证明了分布外数据的可靠模型使用图像的许多高频组件。
translated by 谷歌翻译
研究过程包括许多决定,例如如何应有资格以及在何处发表论文。在本文中,我们介绍了一个一般框架,以调查此类决策的影响。研究效果的主要困难是我们需要了解反事实结果,而实际上并非现实。我们框架的主要见解是灵感来自现有的反事实分析,其中研究人员将双胞胎视为反事实单位。提出的框架将一对彼此引用为双胞胎的论文。这些论文往往是平行的作品,在类似的主题和类似社区中。我们调查了采用不同决策的双论文,观察这些研究带来的研究影响的进展,并通过这些研究的影响来估算决策的影响。我们发布了我们的代码和数据,我们认为由于数据集缺乏反事实研究,因此这是非常有益的。
translated by 谷歌翻译
三维(3D)医学图像的产生可能具有巨大的应用潜力,因为它考虑了3D解剖结构。但是,有两个问题可以防止有效培训3D医疗生成模型:(1)3D医学图像的获取和注释非常昂贵,导致培训图像不足,(2)大量参数是参与3D卷积。为了解决这两个问题,我们提出了一种名为3D Split&Shuffle-Gan的新型GAN模型。为了解决3D数据稀缺问题,我们首先使用丰富的图像切片预先培训二维(2D)GAN模型,并夸大2D卷积权重以改善3D GAN的初始化。为GAN模型的生成器和鉴别器提出了新型的3D网络体系结构,以显着减少参数的数量,同时保持图像生成的质量。研究了许多体重通胀策略和参数有效的3D架构。对心脏(Stanford Aimi冠状动脉钙)和大脑(阿尔茨海默氏病神经成像计划)的实验表明,所提出的方法会导致改善的3D图像产生质量,参数较少。
translated by 谷歌翻译
自我监督学习的最新发展使我们有可能进一步减少人类干预的多步管道中的干预,其中重点围绕着特定感兴趣的对象而发展。在本文中,焦点在组织病理学图像中的细胞核中放置。特别是,我们旨在以无监督的方式提取蜂窝信息,以完成下游任务。随着核以各种尺寸表现出来,我们提出了一个新的依赖量表卷积层来绕过调整核时尺寸的问题。在三个核数据集上,我们基准了以下方法:手工制作的,预先训练的重新系统,有监督的重新系统和自我监督的特征。我们表明,所提出的卷积层提高了性能,并且与Barlows-Twins结合使用,与低样本设置中的监督范式相比,该层可以更好地编码核编码,并且胜过所有其他建议的无监督方法。此外,我们将现有的TNBC数据集扩展到合并核类别的注释,以丰富和公开释放一个小样本设置数据集以进行核分割和分类。
translated by 谷歌翻译