The miniaturization and mobility of computer vision systems are limited by the heavy computational burden and the size of optical lenses. Here, we propose to use a ultra-thin diffractive optical element to implement passive optical convolution. A division adjoint opto-electronic co-design method is also proposed. In our simulation experiments, the first few convolutional layers of the neural network can be replaced by optical convolution in a classification task on the CIFAR-10 dataset with no power consumption, while similar performance can be obtained.
translated by 谷歌翻译
具有最小延迟的人工神经网络的决策对于诸如导航,跟踪和实时机器动作系统之类的许多应用来说是至关重要的。这要求机器学习硬件以高吞吐量处理多维数据。不幸的是,处理卷积操作是数据分类任务的主要计算工具,遵循有挑战性的运行时间复杂性缩放法。然而,在傅立叶光学显示器 - 光处理器中同心地实现卷积定理,使得不迭代的O(1)运行时复杂度以超过1,000×1,000大矩阵的数据输入。在此方法之后,这里我们展示了具有傅里叶卷积神经网络(FCNN)加速器的数据流多核图像批处理。我们将大规模矩阵的图像批量处理显示为傅立叶域中的数字光处理模块执行的被动的2000万点产品乘法。另外,我们通过利用多种时空衍射令并进一步并行化该光学FCNN系统,从而实现了最先进的FCNN加速器的98倍的产量改进。综合讨论与系统能力边缘工作相关的实际挑战突出了傅立叶域和决议缩放法律的串扰问题。通过利用展示技术中的大规模平行性加速卷积带来了基于VAN Neuman的机器学习加速度。
translated by 谷歌翻译
The ever-growing deep learning technologies are making revolutionary changes for modern life. However, conventional computing architectures are designed to process sequential and digital programs, being extremely burdened with performing massive parallel and adaptive deep learning applications. Photonic integrated circuits provide an efficient approach to mitigate bandwidth limitations and power-wall brought by its electronic counterparts, showing great potential in ultrafast and energy-free high-performance computing. Here, we propose an optical computing architecture enabled by on-chip diffraction to implement convolutional acceleration, termed optical convolution unit (OCU). We demonstrate that any real-valued convolution kernels can be exploited by OCU with a prominent computational throughput boosting via the concept of structral re-parameterization. With OCU as the fundamental unit, we build an optical convolutional neural network (oCNN) to implement two popular deep learning tasks: classification and regression. For classification, Fashion-MNIST and CIFAR-4 datasets are tested with accuracy of 91.63% and 86.25%, respectively. For regression, we build an optical denoising convolutional neural network (oDnCNN) to handle Gaussian noise in gray scale images with noise level {\sigma} = 10, 15, 20, resulting clean images with average PSNR of 31.70dB, 29.39dB and 27.72dB, respectively. The proposed OCU presents remarkable performance of low energy consumption and high information density due to its fully passive nature and compact footprint, providing a highly parallel while lightweight solution for future computing architecture to handle high dimensional tensors in deep learning.
translated by 谷歌翻译
计算光学成像(COI)系统利用其设置中的光学编码元素(CE)在单个或多个快照中编码高维场景,并使用计算算法对其进行解码。 COI系统的性能很大程度上取决于其主要组件的设计:CE模式和用于执行给定任务的计算方法。常规方法依赖于随机模式或分析设计来设置CE的分布。但是,深神经网络(DNNS)的可用数据和算法功能已在CE数据驱动的设计中开辟了新的地平线,该设计共同考虑了光学编码器和计算解码器。具体而言,通过通过完全可区分的图像形成模型对COI测量进行建模,该模型考虑了基于物理的光及其与CES的相互作用,可以在端到端优化定义CE和计算解码器的参数和计算解码器(e2e)方式。此外,通过在同一框架中仅优化CE,可以从纯光学器件中执行推理任务。这项工作调查了CE数据驱动设计的最新进展,并提供了有关如何参数化不同光学元素以将其包括在E2E框架中的指南。由于E2E框架可以通过更改损耗功能和DNN来处理不同的推理应用程序,因此我们提出低级任务,例如光谱成像重建或高级任务,例如使用基于任务的光学光学体系结构来增强隐私的姿势估计,以维护姿势估算。最后,我们说明了使用全镜DNN以光速执行的分类和3D对象识别应用程序。
translated by 谷歌翻译
由少量镜头组成的全景环形镜头(PAL)在全景周围具有巨大潜力,该镜头围绕着移动和可穿戴设备的传感任务,因为其尺寸很小,并且视野很大(FOV)。然而,由于缺乏畸变校正的镜头,小体积PAL的图像质量仅限于光学极限。在本文中,我们提出了一个环形计算成像(ACI)框架,以打破轻质PAL设计的光学限制。为了促进基于学习的图像恢复,我们引入了基于波浪的模拟管道,用于全景成像,并通过多个数据分布来应对合成间隙。提出的管道可以轻松地适应具有设计参数的任何PAL,并且适用于宽松的设计。此外,我们考虑了全景成像和物理知识学习的物理先验,我们设计了物理知情的图像恢复网络(PI2RNET)。在数据集级别,我们创建了Divpano数据集,其广泛的实验表明,我们提出的网络在空间变化的降级下在全景图像恢复中设置了新的最新技术。此外,对只有3个球形镜头的简单PAL上提议的ACI的评估揭示了高质量全景成像与紧凑设计之间的微妙平衡。据我们所知,我们是第一个探索PAL中计算成像(CI)的人。代码和数据集将在https://github.com/zju-jiangqi/aci-pi2rnet上公开提供。
translated by 谷歌翻译
The last few years have seen a lot of work to address the challenge of low-latency and high-throughput convolutional neural network inference. Integrated photonics has the potential to dramatically accelerate neural networks because of its low-latency nature. Combined with the concept of Joint Transform Correlator (JTC), the computationally expensive convolution functions can be computed instantaneously (time of flight of light) with almost no cost. This 'free' convolution computation provides the theoretical basis of the proposed PhotoFourier JTC-based CNN accelerator. PhotoFourier addresses a myriad of challenges posed by on-chip photonic computing in the Fourier domain including 1D lenses and high-cost optoelectronic conversions. The proposed PhotoFourier accelerator achieves more than 28X better energy-delay product compared to state-of-art photonic neural network accelerators.
translated by 谷歌翻译
由于深度学习在许多人工智能应用中显示了革命性的性能,其升级的计算需求需要用于巨大并行性的硬件加速器和改进的吞吐量。光学神经网络(ONN)是下一代神经关键组成的有希望的候选者,由于其高并行,低延迟和低能量消耗。在这里,我们设计了一个硬件高效的光子子空间神经网络(PSNN)架构,其针对具有比具有可比任务性能的前一个ONN架构的光学元件使用,区域成本和能量消耗。此外,提供了一种硬件感知培训框架,以最小化所需的设备编程精度,减少芯片区域,并提高噪声鲁棒性。我们在实验上展示了我们的PSNN在蝴蝶式可编程硅光子集成电路上,并在实用的图像识别任务中显示其实用性。
translated by 谷歌翻译
Deploying convolutional neural networks (CNNs) on embedded devices is difficult due to the limited memory and computation resources. The redundancy in feature maps is an important characteristic of those successful CNNs, but has rarely been investigated in neural architecture design. This paper proposes a novel Ghost module to generate more feature maps from cheap operations. Based on a set of intrinsic feature maps, we apply a series of linear transformations with cheap cost to generate many ghost feature maps that could fully reveal information underlying intrinsic features. The proposed Ghost module can be taken as a plug-and-play component to upgrade existing convolutional neural networks. Ghost bottlenecks are designed to stack Ghost modules, and then the lightweight Ghost-Net can be easily established. Experiments conducted on benchmarks demonstrate that the proposed Ghost module is an impressive alternative of convolution layers in baseline models, and our GhostNet can achieve higher recognition performance (e.g. 75.7% top-1 accuracy) than MobileNetV3 with similar computational cost on the ImageNet ILSVRC-2012 classification dataset. Code is available at https: //github.com/huawei-noah/ghostnet.
translated by 谷歌翻译
Ever since the first microscope by Zacharias Janssen in the late 16th century, scientists have been inventing new types of microscopes for various tasks. Inventing a novel architecture demands years, if not decades, worth of scientific experience and creativity. In this work, we introduce Differentiable Microscopy ($\partial\mu$), a deep learning-based design paradigm, to aid scientists design new interpretable microscope architectures. Differentiable microscopy first models a common physics-based optical system however with trainable optical elements at key locations on the optical path. Using pre-acquired data, we then train the model end-to-end for a task of interest. The learnt design proposal can then be simplified by interpreting the learnt optical elements. As a first demonstration, based on the optical 4-$f$ system, we present an all-optical quantitative phase microscope (QPM) design that requires no computational post-reconstruction. A follow-up literature survey suggested that the learnt architecture is similar to the generalized phase contrast method developed two decades ago. Our extensive experiments on multiple datasets that include biological samples show that our learnt all-optical QPM designs consistently outperform existing methods. We experimentally verify the functionality of the optical 4-$f$ system based QPM design using a spatial light modulator. Furthermore, we also demonstrate that similar results can be achieved by an uninterpretable learning based method, namely diffractive deep neural networks (D2NN). The proposed differentiable microscopy framework supplements the creative process of designing new optical systems and would perhaps lead to unconventional but better optical designs.
translated by 谷歌翻译
光学系统的可区分模拟可以与基于深度学习的重建网络结合使用,以通过端到端(E2E)优化光学编码器和深度解码器来实现高性能计算成像。这使成像应用程序(例如3D定位显微镜,深度估计和无透镜摄影)通过优化局部光学编码器。更具挑战性的计算成像应用,例如将3D卷压入单个2D图像的3D快照显微镜,需要高度非本地光学编码器。我们表明,现有的深网解码器具有局部性偏差,可防止这种高度非本地光学编码器的优化。我们使用全球内核傅里叶卷积神经网络(Fouriernets)基于浅神经网络体系结构的解码器来解决此问题。我们表明,在高度非本地分散镜头光学编码器捕获的照片中,傅立叶网络超过了现有的基于网络的解码器。此外,我们表明傅里叶可以对3D快照显微镜的高度非本地光学编码器进行E2E优化。通过将傅立叶网和大规模多GPU可区分的光学模拟相结合,我们能够优化非本地光学编码器170 $ \ times $ \ times $ tos 7372 $ \ times $ \ times $ \ times $比以前的最新状态,并证明了ROI的潜力-type特定的光学编码使用可编程显微镜。
translated by 谷歌翻译
基于我们对红外目标的观察,沿着序列帧内的严重变化很高。在本文中,我们提出了一种动态的重新参数化网络(DRPN)来处理规模变化并平衡红外数据集中的小目标和大目标之间的检测精度。 DRPN采用不同尺寸的卷积内核和动态卷积策略的多个分支。具有不同尺寸卷积粒的多个分支有不同的接收领域大小。动态卷积策略使DRPN自适应重量多个分支。 DRPN可以根据目标的比例变化动态调整接收领域。此外,为了在测试阶段保持有效推断,在训练后通过重新参数化技术进一步将多分支结构转换为单分支结构。关于FLIR,KAIST和INFRAPLANE数据集的广泛实验证明了我们提出的DRPN的有效性。实验结果表明,使用所提出的DRPN作为基本结构而不是SKNET或TridentNET获得了最佳性能的探测器。
translated by 谷歌翻译
使用单像素检测,联合优化编码和解码的端到端神经网络可以实现高精度成像和高电平语义传感。然而,对于不同的采样率,大规模网络需要重新培训,这是呈现的呈现和计算消耗。在这封信中,我们报告了一种加权优化技术,用于动态速率自适应单像素成像和感应,只需要培训网络一次可用于任何采样率的时间一次。具体地,我们在编码过程中引入一种新的加权方案,以表征不同的模式的调制效率。虽然网络以高采样速率训练,但是迭代地更新调制模式和相应的权重,这在融合时产生最佳排名编码串。在实验实施方案中,采用最高重量的最佳模式系列用于光调制,从而实现高效的成像和感测。报告的策略节省了现有动态单像素网络所需另一种低速速率网络的额外培训,这进一步加倍训练效率。验证了Mnist DataSet上的实验,通过采样率为1的网络培训,平均成像PSNR为0.1采样率达到23.50 dB,并且图像的图像分类精度达到高达95.00 \%,以0.03的采样率达到95.00 \% 97.91 \%以0.1的采样率。
translated by 谷歌翻译
在许多图像处理任务中,深度学习方法的成功,最近还将深度学习方法引入了阶段检索问题。这些方法与传统的迭代优化方法不同,因为它们通常只需要一个强度测量,并且可以实时重建相位图像。但是,由于巨大的领域差异,这些方法给出的重建图像的质量仍然有很大的改进空间来满足一般应用要求。在本文中,我们设计了一种新型的深神经网络结构,名为Sisprnet,以基于单个傅立叶强度测量值进行相检索。为了有效利用测量的光谱信息,我们建议使用多层感知器(MLP)作为前端提出一个新的特征提取单元。它允许将输入强度图像的所有像素一起考虑,以探索其全局表示。 MLP的大小经过精心设计,以促进代表性特征的提取,同时减少噪音和异常值。辍学层还可以减轻训练MLP的过度拟合问题。为了促进重建图像中的全局相关性,将自我注意力的机制引入了提议的Sisprnet的上采样和重建(UR)块。这些UR块被插入残留的学习结构中,以防止由于其复杂的层结构而导致的较弱的信息流和消失的梯度问题。使用线性相关幅度和相位的仅相位图像和图像的不同测试数据集对所提出的模型进行了广泛的评估。在光学实验平台上进行了实验,以了解在实用环境中工作时不同深度学习方法的性能。
translated by 谷歌翻译
卷积神经网络(CNN)已广泛用于各个领域并发挥了重要作用。卷积运营商是卷积神经网络的基本组成部分,也是网络培训和推理的最耗时的一部分。近年来,研究人员提出了几种快速卷积算法,包括FFT和Winograd。其中,Winograd卷积显着降低了卷积中的乘法操作,并且还比FFT卷积占据了更少的内存空间。因此,Winograd卷积迅速成为几年内快速卷积实施的首选。目前,卷积算法没有系统概述。本文旨在填补此差距,并为后续研究人员提供详细的参考。本文总结了从算法扩展,算法优化,实现和应用的三个方面的WinoGrad卷积的发展,最后在可能的未来方向上进行了简单的展望。
translated by 谷歌翻译
由于存储器和计算资源有限,部署在移动设备上的卷积神经网络(CNNS)是困难的。我们的目标是通过利用特征图中的冗余来设计包括CPU和GPU的异构设备的高效神经网络,这很少在神经结构设计中进行了研究。对于类似CPU的设备,我们提出了一种新颖的CPU高效的Ghost(C-Ghost)模块,以生成从廉价操作的更多特征映射。基于一组内在的特征映射,我们使用廉价的成本应用一系列线性变换,以生成许多幽灵特征图,可以完全揭示内在特征的信息。所提出的C-Ghost模块可以作为即插即用组件,以升级现有的卷积神经网络。 C-Ghost瓶颈旨在堆叠C-Ghost模块,然后可以轻松建立轻量级的C-Ghostnet。我们进一步考虑GPU设备的有效网络。在建筑阶段的情况下,不涉及太多的GPU效率(例如,深度明智的卷积),我们建议利用阶段明智的特征冗余来制定GPU高效的幽灵(G-GHOST)阶段结构。舞台中的特征被分成两个部分,其中使用具有较少输出通道的原始块处理第一部分,用于生成内在特征,另一个通过利用阶段明智的冗余来生成廉价的操作。在基准测试上进行的实验证明了所提出的C-Ghost模块和G-Ghost阶段的有效性。 C-Ghostnet和G-Ghostnet分别可以分别实现CPU和GPU的准确性和延迟的最佳权衡。代码可在https://github.com/huawei-noah/cv-backbones获得。
translated by 谷歌翻译
In this work we introduce a binarized deep neural network (BDNN) model. BDNNs are trained using a novel binarized back propagation algorithm (BBP), which uses binary weights and binary neurons during the forward and backward propagation, while retaining precision of the stored weights in which gradients are accumulated. At test phase, BDNNs are fully binarized and can be implemented in hardware with low circuit complexity. The proposed binarized networks can be implemented using binary convolutions and proxy matrix multiplications with only standard binary XNOR and population count (popcount) operations. BBP is expected to reduce energy consumption by at least two orders of magnitude when compared to the hardware implementation of existing training algorithms. We obtained near state-of-the-art results with BDNNs on the permutation-invariant MNIST, CIFAR-10 and SVHN datasets.
translated by 谷歌翻译
随着深度神经网络(DNN)的发展以解决日益复杂的问题,它们正受到现有数字处理器的延迟和功耗的限制。为了提高速度和能源效率,已经提出了专门的模拟光学和电子硬件,但是可扩展性有限(输入矢量长度$ k $的数百个元素)。在这里,我们提出了一个可扩展的,单层模拟光学处理器,该光学处理器使用自由空间光学器件可重新配置输入向量和集成的光电,用于静态,可更新的加权和非线性 - 具有$ k \ \ 1,000 $和大约1,000美元和超过。我们通过实验测试MNIST手写数字数据集的分类精度,在没有数据预处理或在硬件上进行数据重新处理的情况下达到94.7%(地面真相96.3%)。我们还确定吞吐量($ \ sim $ 0.9 examac/s)的基本上限,由最大光带宽设置,然后大大增加误差。我们在兼容CMOS兼容系统中宽光谱和空间带宽的组合可以实现下一代DNN的高效计算。
translated by 谷歌翻译
衍射深神经网络(D2NNS)定义了一个由空间工程的被动表面组成的全光计算框架,该框架通过调节传播光的幅度和/或相位来共同处理光学输入信息。衍射光学网络通过薄衍射量以光的速度来完成其计算任务,而无需任何外部计算能力,同时利用了光学的巨大并行性。证明了衍射网络以实现对象的全光分类并执行通用线性变换。在这里,我们首次证明了使用衍射网络的“延时”图像分类方案,通过使用输入对象的横向运动和/或衍射网络,可以显着提高其在复杂输入对象上的分类准确性和概括性性能。 ,相对于彼此。在不同的上下文中,通常将对象和/或相机的相对运动用于图像超分辨率应用程序;受其成功的启发,我们设计了一个延时衍射网络,以受益于由受控或随机横向移动创建的互补信息内容。我们从数值探索了延时衍射网络的设计空间和性能限制,从CIFAR-10数据集的对象进行光学分类中揭示了62.03%的盲测精度。这构成了迄今使用CIFAR-10数据集上的单个衍射网络达到的最高推理精度。延时衍射网络将对使用全光处理器的输入信号的时空分析广泛有用。
translated by 谷歌翻译
我们日常生活中的深度学习是普遍存在的,包括自驾车,虚拟助理,社交网络服务,医疗服务,面部识别等,但是深度神经网络在训练和推理期间需要大量计算资源。该机器学习界主要集中在模型级优化(如深度学习模型的架构压缩),而系统社区则专注于实施级别优化。在其间,在算术界中提出了各种算术级优化技术。本文在模型,算术和实施级技术方面提供了关于资源有效的深度学习技术的调查,并确定了三种不同级别技术的资源有效的深度学习技术的研究差距。我们的调查基于我们的资源效率度量定义,阐明了较低级别技术的影响,并探讨了资源有效的深度学习研究的未来趋势。
translated by 谷歌翻译
Diffractive optical networks provide rich opportunities for visual computing tasks since the spatial information of a scene can be directly accessed by a diffractive processor without requiring any digital pre-processing steps. Here we present data class-specific transformations all-optically performed between the input and output fields-of-view (FOVs) of a diffractive network. The visual information of the objects is encoded into the amplitude (A), phase (P), or intensity (I) of the optical field at the input, which is all-optically processed by a data class-specific diffractive network. At the output, an image sensor-array directly measures the transformed patterns, all-optically encrypted using the transformation matrices pre-assigned to different data classes, i.e., a separate matrix for each data class. The original input images can be recovered by applying the correct decryption key (the inverse transformation) corresponding to the matching data class, while applying any other key will lead to loss of information. The class-specificity of these all-optical diffractive transformations creates opportunities where different keys can be distributed to different users; each user can only decode the acquired images of only one data class, serving multiple users in an all-optically encrypted manner. We numerically demonstrated all-optical class-specific transformations covering A-->A, I-->I, and P-->I transformations using various image datasets. We also experimentally validated the feasibility of this framework by fabricating a class-specific I-->I transformation diffractive network using two-photon polymerization and successfully tested it at 1550 nm wavelength. Data class-specific all-optical transformations provide a fast and energy-efficient method for image and data encryption, enhancing data security and privacy.
translated by 谷歌翻译