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
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
基于卷积神经网络(CNN)的现代单图像超分辨率(SISR)系统实现了花哨的性能,而需要巨大的计算成本。在视觉识别任务中对特征冗余的问题进行了很好的研究,但很少在SISR中进行讨论。基于这样的观察,SISR模型中的许多功能也彼此相似,我们建议使用Shift操作来生成冗余功能(即幽灵功能)。与在类似GPU的设备上耗时的深度卷积相比,Shift操作可以为CNN带来实用的推理加速度。我们分析了SISR操作对SISR任务的好处,并根据Gumbel-SoftMax技巧使Shift取向可学习。此外,基于预训练的模型探索了聚类过程,以识别用于生成内在特征的内在过滤器。幽灵功能将通过沿特定方向移动这些内在功能来得出。最后,完整的输出功能是通过将固有和幽灵特征串联在一起来构建的。在几个基准模型和数据集上进行的广泛实验表明,嵌入了所提出方法的非压缩和轻质SISR模型都可以实现与基准的可比性能,并大大降低了参数,拖台和GPU推荐延迟。例如,我们将参数降低46%,FLOPS掉落46%,而GPU推断潜伏期则减少了$ \ times2 $ EDSR网络的42%,基本上是无损的。
translated by 谷歌翻译
We introduce an extremely computation-efficient CNN architecture named ShuffleNet, which is designed specially for mobile devices with very limited computing power (e.g., 10-150 MFLOPs). The new architecture utilizes two new operations, pointwise group convolution and channel shuffle, to greatly reduce computation cost while maintaining accuracy. Experiments on ImageNet classification and MS COCO object detection demonstrate the superior performance of ShuffleNet over other structures, e.g. lower top-1 error (absolute 7.8%) than recent MobileNet [12] on Ima-geNet classification task, under the computation budget of 40 MFLOPs. On an ARM-based mobile device, ShuffleNet achieves ∼13× actual speedup over AlexNet while maintaining comparable accuracy.
translated by 谷歌翻译
Feature reuse has been a key technique in light-weight convolutional neural networks (CNNs) design. Current methods usually utilize a concatenation operator to keep large channel numbers cheaply (thus large network capacity) by reusing feature maps from other layers. Although concatenation is parameters- and FLOPs-free, its computational cost on hardware devices is non-negligible. To address this, this paper provides a new perspective to realize feature reuse via structural re-parameterization technique. A novel hardware-efficient RepGhost module is proposed for implicit feature reuse via re-parameterization, instead of using concatenation operator. Based on the RepGhost module, we develop our efficient RepGhost bottleneck and RepGhostNet. Experiments on ImageNet and COCO benchmarks demonstrate that the proposed RepGhostNet is much more effective and efficient than GhostNet and MobileNetV3 on mobile devices. Specially, our RepGhostNet surpasses GhostNet 0.5x by 2.5% Top-1 accuracy on ImageNet dataset with less parameters and comparable latency on an ARM-based mobile phone.
translated by 谷歌翻译
Currently, the neural network architecture design is mostly guided by the indirect metric of computation complexity, i.e., FLOPs. However, the direct metric, e.g., speed, also depends on the other factors such as memory access cost and platform characterics. Thus, this work proposes to evaluate the direct metric on the target platform, beyond only considering FLOPs. Based on a series of controlled experiments, this work derives several practical guidelines for efficient network design. Accordingly, a new architecture is presented, called ShuffleNet V2.Comprehensive ablation experiments verify that our model is the stateof-the-art in terms of speed and accuracy tradeoff.
translated by 谷歌翻译
深度学习技术在各种任务中都表现出了出色的有效性,并且深度学习具有推进多种应用程序(包括在边缘计算中)的潜力,其中将深层模型部署在边缘设备上,以实现即时的数据处理和响应。一个关键的挑战是,虽然深层模型的应用通常会产生大量的内存和计算成本,但Edge设备通常只提供非常有限的存储和计算功能,这些功能可能会在各个设备之间差异很大。这些特征使得难以构建深度学习解决方案,以释放边缘设备的潜力,同时遵守其约束。应对这一挑战的一种有希望的方法是自动化有效的深度学习模型的设计,这些模型轻巧,仅需少量存储,并且仅产生低计算开销。该调查提供了针对边缘计算的深度学习模型设计自动化技术的全面覆盖。它提供了关键指标的概述和比较,这些指标通常用于量化模型在有效性,轻度和计算成本方面的水平。然后,该调查涵盖了深层设计自动化技术的三类最新技术:自动化神经体系结构搜索,自动化模型压缩以及联合自动化设计和压缩。最后,调查涵盖了未来研究的开放问题和方向。
translated by 谷歌翻译
在每个卷积层中学习一个静态卷积内核是现代卷积神经网络(CNN)的常见训练范式。取而代之的是,动态卷积的最新研究表明,学习$ n $卷积核与输入依赖性注意的线性组合可以显着提高轻重量CNN的准确性,同时保持有效的推断。但是,我们观察到现有的作品endow卷积内核具有通过一个维度(关于卷积内核编号)的动态属性(关于内核空间的卷积内核编号),但其他三个维度(关于空间大小,输入通道号和输出通道编号和输出通道号,每个卷积内核)被忽略。受到这一点的启发,我们提出了Omni维动态卷积(ODCONV),这是一种更普遍而优雅的动态卷积设计,以推进这一研究。 ODCONV利用了一种新型的多维注意机制,采用平行策略来学习沿着任何卷积层的内核空间的所有四个维度学习卷积内核的互补关注。作为定期卷积的倒数替换,可以将ODCONV插入许多CNN架构中。 ImageNet和MS-Coco数据集的广泛实验表明,ODCONV为包括轻量重量和大型的各种盛行的CNN主链带来了可靠的准确性提升,例如3.77%〜5.71%| 1.86%〜3.72%〜3.72%的绝对1个绝对1改进至ImabivLenetV2 | ImageNet数据集上的重新连接家族。有趣的是,由于其功能学习能力的提高,即使具有一个单个内核的ODCONV也可以与具有多个内核的现有动态卷积对应物竞争或超越现有的动态卷积对应物,从而大大降低了额外的参数。此外,ODCONV也优于其他注意模块,用于调节输出特征或卷积重量。
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
深度卷积神经网络(CNNS)通常是复杂的设计,具有许多可学习的参数,用于准确性原因。为了缓解在移动设备上部署它们的昂贵成本,最近的作品使挖掘预定识别架构中的冗余作出了巨大努力。然而,尚未完全研究现代CNN的输入分辨率的冗余,即输入图像的分辨率是固定的。在本文中,我们观察到,用于准确预测给定图像的最小分辨率使用相同的神经网络是不同的。为此,我们提出了一种新颖的动态分辨率网络(DRNET),其中基于每个输入样本动态地确定输入分辨率。其中,利用所需网络共同地探索具有可忽略的计算成本的分辨率预测器。具体地,预测器学习可以保留的最小分辨率,并且甚至超过每个图像的原始识别准确性。在推断过程中,每个输入图像将被调整为其预测的分辨率,以最小化整体计算负担。然后,我们对几个基准网络和数据集进行了广泛的实验。结果表明,我们的DRNET可以嵌入到任何现成的网络架构中,以获得计算复杂性的相当大降低。例如,DR-RESET-50实现了类似的性能,计算减少约34%,同时增加了1.4%的准确度,与原始Resnet-50上的计算减少相比,在ImageNet上的原始resnet-50增加了10%。
translated by 谷歌翻译
多尺度学习框架已被视为一种能够提高语义分割的能力类别。然而,这个问题并不是微不足道的,尤其是对于现实世界的部署,通常需要高效率推理潜伏期。在本文中,我们彻底分析了卷积块的设计(卷积的类型和卷积中的频道数量),以及跨多个尺度的相互作用方式,所有这些都是从轻量级的语义分割的角度来看。通过这样的深入比较,我们综述了三个原则,因此设计了轻巧且逐渐估计的网络(LPS-NET),这些网络以贪婪的方式在新颖地扩展了网络复杂性。从技术上讲,LPS-NET首先利用了建立小型网络的原则。然后,LPS-NET通过扩展单个维度(卷积块的数量,通道数量或输入分辨率)来逐步扩展到较大网络,以实现最佳的速度/准确性交易。在三个数据集上进行的广泛实验始终证明了LPS-NET优于几种有效的语义分割方法。更值得注意的是,我们的LPS-NET在CityScapes测试套装上达到73.4%MIOU,NVIDIA GTX 1080TI的速度为413.5fps,导致绩效提高1.5%,对抗最高的速度为65% - ART STDC。代码可在\ url {https://github.com/yihengzhang-cv/lps-net}中获得。
translated by 谷歌翻译
In standard Convolutional Neural Networks (CNNs), the receptive fields of artificial neurons in each layer are designed to share the same size. It is well-known in the neuroscience community that the receptive field size of visual cortical neurons are modulated by the stimulus, which has been rarely considered in constructing CNNs. We propose a dynamic selection mechanism in CNNs that allows each neuron to adaptively adjust its receptive field size based on multiple scales of input information. A building block called Selective Kernel (SK) unit is designed, in which multiple branches with different kernel sizes are fused using softmax attention that is guided by the information in these branches. Different attentions on these branches yield different sizes of the effective receptive fields of neurons in the fusion layer. Multiple SK units are stacked to a deep network termed Selective Kernel Networks (SKNets). On the ImageNet and CIFAR benchmarks, we empirically show that SKNet outperforms the existing state-of-the-art architectures with lower model complexity. Detailed analyses show that the neurons in SKNet can capture target objects with different scales, which verifies the capability of neurons for adaptively adjusting their receptive field sizes according to the input. The code and models are available at https://github.com/implus/SKNet.
translated by 谷歌翻译
作为一个非凡的紧凑型型号,ShuffleNetV2提供了一个很好的示例来设计有效的弯头,但很少注意到其极限。在本文中,我们重新考虑了ShufflenetV2的设计模式,并发现频道冗余问题仍然限制了更宽的ShufflenetV2中的散装块的效率提高。为了解决这个问题,我们提出了另一个增强的变种块变体,以类似瓶颈的结构和更隐含的短连接形式。为了验证该构件的有效性,我们进一步建立了一个更强大,更有效的模型家族,称为AugshuffLenets。在CIFAR-10和CIFAR-100数据集上进行了评估,AugshuffLenet始终以较少的计算成本和更少的参数计数来超过ShuffleNetv2的表现。
translated by 谷歌翻译
最近的工作表明,二值化的神经网络(BNN)能够大大降低计算成本和内存占用空间,促进在资源受限设备上进行模型部署。然而,与其全精密对应物相比,BNN患有严重的精度降解。旨在降低这种精度差距的研究已经很大程度上主要集中在具有少量或没有1x1卷积层的特定网络架构上,标准二值化方法不起作用。由于1x1卷积在现代架构的设计中是常见的(例如,Googlenet,Reset,DenSenet),开发一种方法以有效地为BNN进行更广泛采用的方法是至关重要的。在这项工作中,我们提出了一个“弹性链路”(EL)模块,通过自适应地将实值的输入特征自适应地添加到后续卷积输出功能来丰富了BNN内的信息流。所提出的EL模块很容易实现,并且可以与BNN的其他方法结合使用。我们证明将EL添加到BNNS对挑战大规模想象数数据集产生显着改进。例如,我们将二值化resnet26的前1个精度从57.9%提高到64.0%。 EL也有助于培训二值化Mobilenet的趋同,为此实现了56.4%的前1个精度。最后,随着RESTNET的整合,它产生了新的最新的最新性,最新的171.9%的前1个精度。
translated by 谷歌翻译
This paper studies the problem of designing compact binary architectures for vision multi-layer perceptrons (MLPs). We provide extensive analysis on the difficulty of binarizing vision MLPs and find that previous binarization methods perform poorly due to limited capacity of binary MLPs. In contrast with the traditional CNNs that utilizing convolutional operations with large kernel size, fully-connected (FC) layers in MLPs can be treated as convolutional layers with kernel size $1\times1$. Thus, the representation ability of the FC layers will be limited when being binarized, and places restrictions on the capability of spatial mixing and channel mixing on the intermediate features. To this end, we propose to improve the performance of binary MLP (BiMLP) model by enriching the representation ability of binary FC layers. We design a novel binary block that contains multiple branches to merge a series of outputs from the same stage, and also a universal shortcut connection that encourages the information flow from the previous stage. The downsampling layers are also carefully designed to reduce the computational complexity while maintaining the classification performance. Experimental results on benchmark dataset ImageNet-1k demonstrate the effectiveness of the proposed BiMLP models, which achieve state-of-the-art accuracy compared to prior binary CNNs. The MindSpore code is available at \url{https://gitee.com/mindspore/models/tree/master/research/cv/BiMLP}.
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
虽然残留连接使训练非常深的神经网络,但由于其多分支拓扑而​​导致在线推断不友好。这鼓励许多研究人员在推动时没有残留连接的情况下设计DNN。例如,repvgg在部署时将多分支拓扑重新参数化为vgg型(单分支)模型,当网络相对较浅时显示出具有很大的性能。但是,RepVGG不能等效地将Reset转换为VGG,因为重新参数化方法只能应用于线性块,并且必须将非线性层(Relu)放在残余连接之外,这导致了有限的表示能力,特别是更深入网络。在本文中,我们的目标是通过在Resblock上的保留和合并(RM)操作等效地纠正此问题,并提出删除Vanilla Reset中的残留连接。具体地,RM操作允许输入特征映射通过块,同时保留其信息,并在每个块的末尾合并所有信息,这可以去除残差而不改变原始输出。作为一个插件方法,RM操作基本上有三个优点:1)其实现使其实现高比率网络修剪。 2)它有助于打破RepVGG的深度限制。 3)与Reset和RepVGG相比,它导致更好的精度速度折衷网络(RMNet)。我们相信RM操作的意识形态可以激发对未来社区的模型设计的许多见解。代码可用:https://github.com/fxmeng/rmnet。
translated by 谷歌翻译
Representing features at multiple scales is of great importance for numerous vision tasks. Recent advances in backbone convolutional neural networks (CNNs) continually demonstrate stronger multi-scale representation ability, leading to consistent performance gains on a wide range of applications. However, most existing methods represent the multi-scale features in a layerwise manner. In this paper, we propose a novel building block for CNNs, namely Res2Net, by constructing hierarchical residual-like connections within one single residual block. The Res2Net represents multi-scale features at a granular level and increases the range of receptive fields for each network layer. The proposed Res2Net block can be plugged into the state-of-the-art backbone CNN models, e.g., ResNet, ResNeXt, and DLA. We evaluate the Res2Net block on all these models and demonstrate consistent performance gains over baseline models on widely-used datasets, e.g., CIFAR-100 and ImageNet. Further ablation studies and experimental results on representative computer vision tasks, i.e., object detection, class activation mapping, and salient object detection, further verify the superiority of the Res2Net over the state-of-the-art baseline methods. The source code and trained models are available on https://mmcheng.net/res2net/.
translated by 谷歌翻译
在本文中,我们通过利用视觉数据中的空间稀疏性提出了一种新的模型加速方法。我们观察到,视觉变压器中的最终预测仅基于最有用的令牌的子集,这足以使图像识别。基于此观察,我们提出了一个动态的令牌稀疏框架,以根据加速视觉变压器的输入逐渐和动态地修剪冗余令牌。具体而言,我们设计了一个轻量级预测模块,以估计给定当前功能的每个令牌的重要性得分。该模块被添加到不同的层中以层次修剪冗余令牌。尽管该框架的启发是我们观察到视觉变压器中稀疏注意力的启发,但我们发现自适应和不对称计算的想法可能是加速各种体系结构的一般解决方案。我们将我们的方法扩展到包括CNN和分层视觉变压器在内的层次模型,以及更复杂的密集预测任务,这些任务需要通过制定更通用的动态空间稀疏框架,并具有渐进性的稀疏性和非对称性计算,用于不同空间位置。通过将轻质快速路径应用于少量的特征,并使用更具表现力的慢速路径到更重要的位置,我们可以维护特征地图的结构,同时大大减少整体计算。广泛的实验证明了我们框架对各种现代体系结构和不同视觉识别任务的有效性。我们的结果清楚地表明,动态空间稀疏为模型加速提供了一个新的,更有效的维度。代码可从https://github.com/raoyongming/dynamicvit获得
translated by 谷歌翻译
被广泛采用的缩减采样是为了在视觉识别的准确性和延迟之间取得良好的权衡。不幸的是,没有学习常用的合并层,因此无法保留重要信息。作为另一个降低方法,自适应采样权重和与任务相关的过程区域,因此能够更好地保留有用的信息。但是,自适应采样的使用仅限于某些层。在本文中,我们表明,在深神经网络的构件中使用自适应采样可以提高其效率。特别是,我们提出了SSBNET,该SSBNET是通过将采样层反复插入Resnet等现有网络构建的。实验结果表明,所提出的SSBNET可以在ImageNet和可可数据集上实现竞争性图像分类和对象检测性能。例如,SSB-Resnet-RS-200在Imagenet数据集上的精度达到82.6%,比基线RESNET-RS-152高0.6%,具有相似的复杂性。可视化显示了SSBNET在允许不同层专注于不同位置的优势,而消融研究进一步验证了自适应采样比均匀方法的优势。
translated by 谷歌翻译