We propose a novel antialiasing method to increase shift invariance in convolutional neural networks (CNNs). More precisely, we replace the conventional combination "real-valued convolutions + max pooling" ($\mathbb R$Max) by "complex-valued convolutions + modulus" ($\mathbb C$Mod), which produce stable feature representations for band-pass filters with well-defined orientations. In a recent work, we proved that, for such filters, the two operators yield similar outputs. Therefore, $\mathbb C$Mod can be viewed as a stable alternative to $\mathbb R$Max. To separate band-pass filters from other freely-trained kernels, in this paper, we designed a "twin" architecture based on the dual-tree complex wavelet packet transform, which generates similar outputs as standard CNNs with fewer trainable parameters. In addition to improving stability to small shifts, our experiments on AlexNet and ResNet showed increased prediction accuracy on natural image datasets such as ImageNet and CIFAR10. Furthermore, our approach outperformed recent antialiasing methods based on low-pass filtering by preserving high-frequency information, while reducing memory usage.
translated by 谷歌翻译
We introduce Group equivariant Convolutional Neural Networks (G-CNNs), a natural generalization of convolutional neural networks that reduces sample complexity by exploiting symmetries. G-CNNs use G-convolutions, a new type of layer that enjoys a substantially higher degree of weight sharing than regular convolution layers. G-convolutions increase the expressive capacity of the network without increasing the number of parameters. Group convolution layers are easy to use and can be implemented with negligible computational overhead for discrete groups generated by translations, reflections and rotations. G-CNNs achieve state of the art results on CI-FAR10 and rotated MNIST.
translated by 谷歌翻译
Modern convolutional networks are not shiftinvariant, as small input shifts or translations can cause drastic changes in the output. Commonly used downsampling methods, such as max-pooling, strided-convolution, and averagepooling, ignore the sampling theorem. The wellknown signal processing fix is anti-aliasing by low-pass filtering before downsampling. However, simply inserting this module into deep networks degrades performance; as a result, it is seldomly used today. We show that when integrated correctly, it is compatible with existing architectural components, such as max-pooling and strided-convolution. We observe increased accuracy in ImageNet classification, across several commonly-used architectures, such as ResNet, DenseNet, and MobileNet, indicating effective regularization. Furthermore, we observe better generalization, in terms of stability and robustness to input corruptions. Our results demonstrate that this classical signal processing technique has been undeservingly overlooked in modern deep networks.
translated by 谷歌翻译
Translating or rotating an input image should not affect the results of many computer vision tasks. Convolutional neural networks (CNNs) are already translation equivariant: input image translations produce proportionate feature map translations. This is not the case for rotations. Global rotation equivariance is typically sought through data augmentation, but patch-wise equivariance is more difficult. We present Harmonic Networks or H-Nets, a CNN exhibiting equivariance to patch-wise translation and 360-rotation. We achieve this by replacing regular CNN filters with circular harmonics, returning a maximal response and orientation for every receptive field patch.H-Nets use a rich, parameter-efficient and fixed computational complexity representation, and we show that deep feature maps within the network encode complicated rotational invariants. We demonstrate that our layers are general enough to be used in conjunction with the latest architectures and techniques, such as deep supervision and batch normalization. We also achieve state-of-the-art classification on rotated-MNIST, and competitive results on other benchmark challenges.
translated by 谷歌翻译
手写数字识别(HDR)是光学特征识别(OCR)领域中最具挑战性的任务之一。不管语言如何,HDR都存在一些固有的挑战,这主要是由于个人跨个人的写作风格的变化,编写媒介和环境的变化,无法在反复编写任何数字等时保持相同的笔触。除此之外,特定语言数字的结构复杂性可能会导致HDR的模棱两可。多年来,研究人员开发了许多离线和在线HDR管道,其中不同的图像处理技术与传统的机器学习(ML)基于基于的和/或基于深度学习(DL)的体系结构相结合。尽管文献中存在有关HDR的广泛审查研究的证据,例如:英语,阿拉伯语,印度,法尔西,中文等,但几乎没有对孟加拉人HDR(BHDR)的调查,这缺乏对孟加拉语HDR(BHDR)的研究,而这些调查缺乏对孟加拉语HDR(BHDR)的研究。挑战,基础识别过程以及可能的未来方向。在本文中,已经分析了孟加拉语手写数字的特征和固有的歧义,以及二十年来最先进的数据集的全面见解和离线BHDR的方法。此外,还详细讨论了一些涉及BHDR的现实应用特定研究。本文还将作为对离线BHDR背后科学感兴趣的研究人员的汇编,煽动了对相关研究的新途径的探索,这可能会进一步导致在不同应用领域对孟加拉语手写数字进行更好的离线认识。
translated by 谷歌翻译
从随机字段或纹理中提取信息是科学中无处不在的任务,从探索性数据分析到分类和参数估计。从物理学到生物学,它往往通过功率谱分析来完成,这通常过于有限,或者使用需要大型训练的卷积神经网络(CNNS)并缺乏解释性。在本文中,我们倡导使用散射变换(Mallat 2012),这是一种强大的统计数据,它来自CNNS的数学思想,但不需要任何培训,并且是可解释的。我们表明它提供了一种相对紧凑的汇总统计数据,具有视觉解释,并在广泛的科学应用中携带大多数相关信息。我们向该估算者提供了非技术性介绍,我们认为它可以使数据分析有利于多种科学领域的模型和参数推断。有趣的是,了解散射变换的核心操作允许人们解读CNN的内部工作的许多关键方面。
translated by 谷歌翻译
The principle of equivariance to symmetry transformations enables a theoretically grounded approach to neural network architecture design. Equivariant networks have shown excellent performance and data efficiency on vision and medical imaging problems that exhibit symmetries. Here we show how this principle can be extended beyond global symmetries to local gauge transformations. This enables the development of a very general class of convolutional neural networks on manifolds that depend only on the intrinsic geometry, and which includes many popular methods from equivariant and geometric deep learning.We implement gauge equivariant CNNs for signals defined on the surface of the icosahedron, which provides a reasonable approximation of the sphere. By choosing to work with this very regular manifold, we are able to implement the gauge equivariant convolution using a single conv2d call, making it a highly scalable and practical alternative to Spherical CNNs. Using this method, we demonstrate substantial improvements over previous methods on the task of segmenting omnidirectional images and global climate patterns.
translated by 谷歌翻译
Training generative adversarial networks (GAN) using too little data typically leads to discriminator overfitting, causing training to diverge. We propose an adaptive discriminator augmentation mechanism that significantly stabilizes training in limited data regimes. The approach does not require changes to loss functions or network architectures, and is applicable both when training from scratch and when fine-tuning an existing GAN on another dataset. We demonstrate, on several datasets, that good results are now possible using only a few thousand training images, often matching StyleGAN2 results with an order of magnitude fewer images. We expect this to open up new application domains for GANs. We also find that the widely used CIFAR-10 is, in fact, a limited data benchmark, and improve the record FID from 5.59 to 2.42.
translated by 谷歌翻译
我们研究复杂的缩放作为一种自然的对称性和复杂的测量和表示独特的对称性。深度复杂网络(DCN)将实值的代数扩展到复杂域,而不会解决复杂值缩放。超现实占据复杂数字的限制性歧管视图,采用距离度量来实现复杂的缩放不变性,同时丢失丰富的复合值。我们分析了复杂的缩放,作为共同领域的转换和设计新颖的具有这种特殊转换的不变神经网络层。我们还提出了RGB图像的新型复合值表示,其中复值缩放表示色调偏移或跨色通道的相关变化。在MSTAR,CIFAR10,CIFAR100和SVHN上基准测试,我们的共同域对称(CDS)分类器提供更高的准确性,更好的泛化,对共同域变换的鲁棒性,以及比DCN和超现实的更低模型偏差和方差,具有较少的参数。
translated by 谷歌翻译
小波散射变换创造了几何不变和变形稳定性。在多个信号域中,与其他非学习表示形式相比,它可以产生更多的判别性表示,并且在某些任务中,尤其是在有限的标记数据和高度结构化的信号中,它都超越了学习的表示。通常选择散射转换中使用的小波过滤器,以通过参数化的母小波创建紧密的框架。在这项工作中,我们研究了这种标准的小波滤网构造是否最佳。为了关注Morlet小波,我们建议学习过滤器的量表,方向和纵横比,以产生散射变换的特定问题参数化。我们表明,我们学到的散射转换版本在标准散射变换上在小样本分类设置中产生了显着的性能增长。此外,我们的经验结果表明,传统的滤纸结构对于提取有效表示的散射转换可能并不总是必要的。
translated by 谷歌翻译
标准情况被出现为对构成组的身份保留转换的物体表示的理想性质,例如翻译和旋转。然而,由组标准规定的表示的表示的表现仍然不完全理解。我们通过提供封面函数计数定理的概括来解决这个差距,这些定理量化了可以分配给物体的等异点的线性可分离和组不变二进制二分层的数量。我们发现可分离二分法的分数由由组动作固定的空间的尺寸决定。我们展示了该关系如何扩展到卷积,元素 - 明智的非线性和全局和本地汇集等操作。虽然其他操作不会改变可分离二分法的分数,但尽管是高度非线性操作,但是局部汇集减少了分数。最后,我们在随机初始化和全培训的卷积神经网络的中间代表中测试了我们的理论,并找到了完美的协议。
translated by 谷歌翻译
我们提出了一种多移民通道(MGIC)方法,该方法可以解决参数数量相对于标准卷积神经网络(CNN)中的通道数的二次增长。因此,我们的方法解决了CNN中的冗余,这也被轻量级CNN的成功所揭示。轻巧的CNN可以达到与参数较少的标准CNN的可比精度。但是,权重的数量仍然随CNN的宽度四倍地缩放。我们的MGIC体系结构用MGIC对应物代替了每个CNN块,该块利用了小组大小的嵌套分组卷积的层次结构来解决此问题。因此,我们提出的架构相对于网络的宽度线性扩展,同时保留了通道的完整耦合,如标准CNN中。我们对图像分类,分割和点云分类进行的广泛实验表明,将此策略应用于Resnet和MobilenetV3等不同体系结构,可以减少参数的数量,同时获得相似或更好的准确性。
translated by 谷歌翻译
将组对称性直接纳入学习过程,已被证明是模型设计的有效准则。通过生产保证对输入上的组动作改造协议的功能,Group-Secrivariant卷积神经网络(G-CNN)在具有内在对称的学习任务中实现了显着改善的泛化性能。已经研究了G-CNNS的一般理论和实际实施,用于旋转或缩放变换下的平面图像,但仅是单独的。在本文中,我们存在roto-scale-pranslance的CNN(RST-CNN),保证通过耦合组卷积来实现这三个组的增义性。此外,随着现实中的对称变换很少是非常完美的并且通常会受到输入变形的影响,我们提供了对输入失真的表示的等意识的稳定性分析,这激励了(预固定)低频空间下的卷积滤波器的截断扩展模式。所得到的模型可被证明可以实现变形 - 稳健的RST标准,即RST对称性仍然“大约”保存,当通过滋扰数据变形时“被污染”,这是对分布外概述尤为重要的属性。 Mnist,Fashion-Mnist和STL-10的数值实验表明,所提出的模型在现有技术中产生显着的增益,尤其是在数据内旋转和缩放变化的小数据制度中。
translated by 谷歌翻译
多层erceptron(MLP),作为出现的第一个神经网络结构,是一个大的击中。但是由硬件计算能力和数据集的大小限制,它一旦沉没了数十年。在此期间,我们目睹了从手动特征提取到带有局部接收领域的CNN的范式转变,以及基于自我关注机制的全球接收领域的变换。今年(2021年),随着MLP混合器的推出,MLP已重新进入敏捷,并吸引了计算机视觉界的广泛研究。与传统的MLP进行比较,它变得更深,但改变了完全扁平化以补丁平整的输入。鉴于其高性能和较少的需求对视觉特定的感应偏见,但社区无法帮助奇迹,将MLP,最简单的结构与全球接受领域,但没有关注,成为一个新的电脑视觉范式吗?为了回答这个问题,本调查旨在全面概述视觉深层MLP模型的最新发展。具体而言,我们从微妙的子模块设计到全局网络结构,我们审查了这些视觉深度MLP。我们比较了不同网络设计的接收领域,计算复杂性和其他特性,以便清楚地了解MLP的开发路径。调查表明,MLPS的分辨率灵敏度和计算密度仍未得到解决,纯MLP逐渐发展朝向CNN样。我们建议,目前的数据量和计算能力尚未准备好接受纯的MLP,并且人工视觉指导仍然很重要。最后,我们提供了开放的研究方向和可能的未来作品的分析。我们希望这项努力能够点燃社区的进一步兴趣,并鼓励目前为神经网络进行更好的视觉量身定制设计。
translated by 谷歌翻译
图像生物标准化倡议(IBSI)旨在通过标准化从图像中提取图像生物标志物(特征)的计算过程来提高射致研究的再现性。我们之前建立了169个常用特征的参考值,创建了标准的射频图像处理方案,并开发了用于垄断研究的报告指南。但是,若干方面没有标准化。在这里,我们提出了在射频中使用卷积图像过滤器的参考手册的初步版本。滤波器,例如高斯滤波器的小波或拉普拉斯,在强调特定图像特征(如边缘和Blob)中发挥重要组成部分。已发现从过滤滤波器响应图派生的功能可重复差。此参考手册构成了持续工作的基础,用于标准化卷积滤波器中的覆盖物中的持续工作,并在这项工作进行时更新。
translated by 谷歌翻译
生成的对抗网络由于研究人员的最新性能在生成新图像时仅使用目标分布的数据集,因此引起了研究人员的关注。已经表明,真实图像的频谱和假图像之间存在差异。由于傅立叶变换是一种徒图映射,因此说该模型在学习原始分布方面有一个重大问题是一个公平的结论。在这项工作中,我们研究了当前gan的架构和数学理论中提到的缺点的可能原因。然后,我们提出了一个新模型,以减少实际图像和假图像频谱之间的差异。为此,我们使用几何深度学习的蓝图为频域设计了一个全新的架构。然后,我们通过将原始数据的傅立叶域表示作为训练过程中的主要特征来表明生成图像的质量的有希望的改善。
translated by 谷歌翻译
While machine learning is traditionally a resource intensive task, embedded systems, autonomous navigation, and the vision of the Internet of Things fuel the interest in resource-efficient approaches. These approaches aim for a carefully chosen trade-off between performance and resource consumption in terms of computation and energy. The development of such approaches is among the major challenges in current machine learning research and key to ensure a smooth transition of machine learning technology from a scientific environment with virtually unlimited computing resources into everyday's applications. In this article, we provide an overview of the current state of the art of machine learning techniques facilitating these real-world requirements. In particular, we focus on deep neural networks (DNNs), the predominant machine learning models of the past decade. We give a comprehensive overview of the vast literature that can be mainly split into three non-mutually exclusive categories: (i) quantized neural networks, (ii) network pruning, and (iii) structural efficiency. These techniques can be applied during training or as post-processing, and they are widely used to reduce the computational demands in terms of memory footprint, inference speed, and energy efficiency. We also briefly discuss different concepts of embedded hardware for DNNs and their compatibility with machine learning techniques as well as potential for energy and latency reduction. We substantiate our discussion with experiments on well-known benchmark datasets using compression techniques (quantization, pruning) for a set of resource-constrained embedded systems, such as CPUs, GPUs and FPGAs. The obtained results highlight the difficulty of finding good trade-offs between resource efficiency and predictive performance.
translated by 谷歌翻译
We observe that despite their hierarchical convolutional nature, the synthesis process of typical generative adversarial networks depends on absolute pixel coordinates in an unhealthy manner. This manifests itself as, e.g., detail appearing to be glued to image coordinates instead of the surfaces of depicted objects. We trace the root cause to careless signal processing that causes aliasing in the generator network. Interpreting all signals in the network as continuous, we derive generally applicable, small architectural changes that guarantee that unwanted information cannot leak into the hierarchical synthesis process. The resulting networks match the FID of StyleGAN2 but differ dramatically in their internal representations, and they are fully equivariant to translation and rotation even at subpixel scales. Our results pave the way for generative models better suited for video and animation. * This work was done during an internship at NVIDIA. 35th Conference on Neural Information Processing Systems (NeurIPS 2021).
translated by 谷歌翻译
在这项工作中,我们设计了一个完全复杂的神经网络,用于虹膜识别的任务。与一般物体识别的问题不同,在实际值的神经网络可以用于提取相关特征的情况下,虹膜识别取决于从输入的虹膜纹理提取两个相位和幅度信息,以便更好地表示其生物识别内容。这需要提取和处理不能由实值神经网络有效处理的相位信息。在这方面,我们设计了一个完全复杂的神经网络,可以更好地捕获虹膜纹理的多尺度,多分辨率和多向阶段和多向阶段和幅度特征。我们展示了具有用于生成经典iRIscode的Gabor小波的提出的复合值虹膜识别网络的强烈对应关系;然而,所提出的方法使得能够为IRIS识别量身定​​制的自动复数特征学习的新能力。我们对三个基准数据集进行实验 - Nd-Crosssensor-2013,Casia-Iris-千和Ubiris.v2 - 并显示了拟议网络的虹膜识别任务的好处。我们利用可视化方案来传达复合网络的方式,与标准的实际网络相比,从虹膜纹理提取根本不同的特征。
translated by 谷歌翻译
部分微分方程(PDE)参见在科学和工程中的广泛使用,以将物理过程的模拟描述为标量和向量场随着时间的推移相互作用和协调。由于其标准解决方案方法的计算昂贵性质,神经PDE代理已成为加速这些模拟的积极研究主题。但是,当前的方法并未明确考虑不同字段及其内部组件之间的关系,这些关系通常是相关的。查看此类相关场的时间演变通过多活动场的镜头,使我们能够克服这些局限性。多胎场由标量,矢量以及高阶组成部分组成,例如双分数和三分分射线。 Clifford代数可以描述它们的代数特性,例如乘法,加法和其他算术操作。据我们所知,本文介绍了此类多人表示的首次使用以及Clifford的卷积和Clifford Fourier在深度学习的背景下的转换。由此产生的Clifford神经层普遍适用,并将在流体动力学,天气预报和一般物理系统的建模领域中直接使用。我们通过经验评估克利福德神经层的好处,通过在二维Navier-Stokes和天气建模任务以及三维Maxwell方程式上取代其Clifford对应物中常见的神经PDE代理中的卷积和傅立叶操作。克利福德神经层始终提高测试神经PDE代理的概括能力。
translated by 谷歌翻译