We present the next generation of MobileNets based on a combination of complementary search techniques as well as a novel architecture design. MobileNetV3 is tuned to mobile phone CPUs through a combination of hardwareaware network architecture search (NAS) complemented by the NetAdapt algorithm and then subsequently improved through novel architecture advances. This paper starts the exploration of how automated search algorithms and network design can work together to harness complementary approaches improving the overall state of the art. Through this process we create two new MobileNet models for release: MobileNetV3-Large and MobileNetV3-Small which are targeted for high and low resource use cases. These models are then adapted and applied to the tasks of object detection and semantic segmentation. For the task of semantic segmentation (or any dense pixel prediction), we propose a new efficient segmentation decoder Lite Reduced Atrous Spatial Pyramid Pooling (LR-ASPP). We achieve new state of the art results for mobile classification, detection and segmentation. MobileNetV3-Large is 3.2% more accurate on ImageNet classification while reducing latency by 20% compared to MobileNetV2. MobileNetV3-Small is 6.6% more accurate compared to a MobileNetV2 model with comparable latency. MobileNetV3-Large detection is over 25% faster at roughly the same accuracy as Mo-bileNetV2 on COCO detection. MobileNetV3-Large LR-ASPP is 34% faster than MobileNetV2 R-ASPP at similar accuracy for Cityscapes segmentation.

Designing convolutional neural networks (CNN) for mobile devices is challenging because mobile models need to be small and fast, yet still accurate. Although significant efforts have been dedicated to design and improve mobile CNNs on all dimensions, it is very difficult to manually balance these trade-offs when there are so many architectural possibilities to consider. In this paper, we propose an automated mobile neural architecture search (MNAS) approach, which explicitly incorporate model latency into the main objective so that the search can identify a model that achieves a good trade-off between accuracy and latency. Unlike previous work, where latency is considered via another, often inaccurate proxy (e.g., FLOPS), our approach directly measures real-world inference latency by executing the model on mobile phones. To further strike the right balance between flexibility and search space size, we propose a novel factorized hierarchical search space that encourages layer diversity throughout the network. Experimental results show that our approach consistently outperforms state-of-the-art mobile CNN models across multiple vision tasks. On the ImageNet classification task, our MnasNet achieves 75.2% top-1 accuracy with 78ms latency on a Pixel phone, which is 1.8× faster than MobileNetV2 [29] with 0.5% higher accuracy and 2.3× faster than NASNet [36] with 1.2% higher accuracy. Our MnasNet also achieves better mAP quality than MobileNets for COCO object detection. Code is at https://github.com/tensorflow/tpu/ tree/master/models/official/mnasnet.

In this paper we describe a new mobile architecture, MobileNetV2, that improves the state of the art performance of mobile models on multiple tasks and benchmarks as well as across a spectrum of different model sizes. We also describe efficient ways of applying these mobile models to object detection in a novel framework we call SSDLite. Additionally, we demonstrate how to build mobile semantic segmentation models through a reduced form of DeepLabv3 which we call Mobile DeepLabv3.is based on an inverted residual structure where the shortcut connections are between the thin bottleneck layers. The intermediate expansion layer uses lightweight depthwise convolutions to filter features as a source of non-linearity. Additionally, we find that it is important to remove non-linearities in the narrow layers in order to maintain representational power. We demonstrate that this improves performance and provide an intuition that led to this design.Finally, our approach allows decoupling of the input/output domains from the expressiveness of the transformation, which provides a convenient framework for further analysis. We measure our performance on ImageNet [1] classification, COCO object detection [2], VOC image segmentation [3]. We evaluate the trade-offs between accuracy, and number of operations measured by multiply-adds (MAdd), as well as actual latency, and the number of parameters.

我们展示了一个下一代神经网络架构，马赛克，用于移动设备上的高效和准确的语义图像分割。MOSAIC是通过各种移动硬件平台使用常用的神经操作设计，以灵活地部署各种移动平台。利用简单的非对称编码器 - 解码器结构，该解码器结构由有效的多尺度上下文编码器和轻量级混合解码器组成，以从聚合信息中恢复空间细节，Mosaic在平衡准确度和计算成本的同时实现了新的最先进的性能。基于搜索的分类网络，马赛克部署在定制的特征提取骨架顶部，达到目前行业标准MLPerf型号和最先进的架构，达到5％的绝对精度增益。

在这项工作中，我们提出了一种方法，以准确评估和比较有效的神经网络构建块的性能，以硬件感知方式进行计算机视觉。我们的比较使用了基于设计空间的随机采样网络的帕累托前沿来捕获潜在的准确性/复杂性权衡。我们表明，我们的方法允许通过以前的比较范例获得的信息匹配，但对硬件成本和准确性之间的关系提供了更多见解。我们使用我们的方法来分析不同的构件并评估其在一系列嵌入式硬件平台上的性能。这突出了基准构建块作为神经网络设计过程中的预选步骤的重要性。我们表明，选择合适的构件可以在特定硬件ML加速器上加快推理的速度2倍。

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。

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。

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.

With the success of Vision Transformers (ViTs) in computer vision tasks, recent arts try to optimize the performance and complexity of ViTs to enable efficient deployment on mobile devices. Multiple approaches are proposed to accelerate attention mechanism, improve inefficient designs, or incorporate mobile-friendly lightweight convolutions to form hybrid architectures. However, ViT and its variants still have higher latency or considerably more parameters than lightweight CNNs, even true for the years-old MobileNet. In practice, latency and size are both crucial for efficient deployment on resource-constraint hardware. In this work, we investigate a central question, can transformer models run as fast as MobileNet and maintain a similar size? We revisit the design choices of ViTs and propose an improved supernet with low latency and high parameter efficiency. We further introduce a fine-grained joint search strategy that can find efficient architectures by optimizing latency and number of parameters simultaneously. The proposed models, EfficientFormerV2, achieve about $4\%$ higher top-1 accuracy than MobileNetV2 and MobileNetV2$\times1.4$ on ImageNet-1K with similar latency and parameters. We demonstrate that properly designed and optimized vision transformers can achieve high performance with MobileNet-level size and speed.

为了实现不断增长的准确性，通常会开发大型和复杂的神经网络。这样的模型需要高度的计算资源，因此不能在边缘设备上部署。由于它们在几个应用领域的有用性，建立资源有效的通用网络非常感兴趣。在这项工作中，我们努力有效地结合了CNN和变压器模型的优势，并提出了一种新的有效混合体系结构。特别是在EDGENEXT中，我们引入了分裂深度转置注意力（SDTA）编码器，该编码器将输入张量分解为多个通道组，并利用深度旋转以及跨通道维度的自我注意力，以隐含地增加接受场并编码多尺度特征。我们在分类，检测和分割任务上进行的广泛实验揭示了所提出的方法的优点，优于相对较低的计算要求的最先进方法。我们具有130万参数的EDGENEXT模型在Imagenet-1k上达到71.2 \％TOP-1的精度，超过移动设备的绝对增益为2.2 \％，而拖鞋减少了28 \％。此外，我们具有560万参数的EDGENEXT模型在Imagenet-1k上达到了79.4 \％TOP-1的精度。代码和模型可在https://t.ly/_vu9上公开获得。

Spatial pyramid pooling module or encode-decoder structure are used in deep neural networks for semantic segmentation task. The former networks are able to encode multi-scale contextual information by probing the incoming features with filters or pooling operations at multiple rates and multiple effective fields-of-view, while the latter networks can capture sharper object boundaries by gradually recovering the spatial information. In this work, we propose to combine the advantages from both methods. Specifically, our proposed model, DeepLabv3+, extends DeepLabv3 by adding a simple yet effective decoder module to refine the segmentation results especially along object boundaries. We further explore the Xception model and apply the depthwise separable convolution to both Atrous Spatial Pyramid Pooling and decoder modules, resulting in a faster and stronger encoder-decoder network. We demonstrate the effectiveness of the proposed model on PASCAL VOC 2012 and Cityscapes datasets, achieving the test set performance of 89.0% and 82.1% without any post-processing. Our paper is accompanied with a publicly available reference implementation of the proposed models in Tensorflow at https: //github.com/tensorflow/models/tree/master/research/deeplab.

语义分割是将类标签分配给图像中每个像素的问题，并且是自动车辆视觉堆栈的重要组成部分，可促进场景的理解和对象检测。但是，许多表现最高的语义分割模型非常复杂且笨拙，因此不适合在计算资源有限且低延迟操作的板载自动驾驶汽车平台上部署。在这项调查中，我们彻底研究了旨在通过更紧凑，更有效的模型来解决这种未对准的作品，该模型能够在低内存嵌入式系统上部署，同时满足实时推理的限制。我们讨论了该领域中最杰出的作品，根据其主要贡献将它们置于分类法中，最后我们评估了在一致的硬件和软件设置下，所讨论模型的推理速度，这些模型代表了具有高端的典型研究环境GPU和使用低内存嵌入式GPU硬件的现实部署方案。我们的实验结果表明，许多作品能够在资源受限的硬件上实时性能，同时说明延迟和准确性之间的一致权衡。

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.

Recently, Neural Architecture Search (NAS) has successfully identified neural network architectures that exceed human designed ones on large-scale image classification. In this paper, we study NAS for semantic image segmentation. Existing works often focus on searching the repeatable cell structure, while hand-designing the outer network structure that controls the spatial resolution changes. This choice simplifies the search space, but becomes increasingly problematic for dense image prediction which exhibits a lot more network level architectural variations. Therefore, we propose to search the network level structure in addition to the cell level structure, which forms a hierarchical architecture search space. We present a network level search space that includes many popular designs, and develop a formulation that allows efficient gradient-based architecture search (3 P100 GPU days on Cityscapes images). We demonstrate the effectiveness of the proposed method on the challenging Cityscapes, PASCAL VOC 2012, and ADE20K datasets. Auto-DeepLab, our architecture searched specifically for semantic image segmentation, attains state-of-the-art performance without any ImageNet pretraining. 1 * Work done while an intern at Google.

是否可以在深网络中重组非线性激活函数以创建硬件有效的模型？为了解决这个问题，我们提出了一个称为重组激活网络（RANS）的新范式，该范式操纵模型中的非线性数量以提高其硬件意识和效率。首先，我们提出了RAN-STHICER（RAN-E） - 一个新的硬件感知搜索空间和半自动搜索算法 - 用硬件感知的块替换效率低下的块。接下来，我们提出了一种称为RAN-IMPLICIC（RAN-I）的无训练模型缩放方法，从理论上讲，我们在非线性单元的数量方面证明了网络拓扑与其表现性之间的联系。我们证明，我们的网络在不同尺度和几种类型的硬件上实现最新的成像网结果。例如，与有效网络-lite-B0相比，RAN-E在ARM Micro-NPU上每秒（FPS）提高了1.5倍，同时提高了类似的精度。另一方面，ran-i以相似或更好的精度表现出#macs的#macs降低2倍。我们还表明，在基于ARM的数据中心CPU上，RAN-I的FPS比Convnext高40％。最后，与基于Convnext的模型相比，基于RAN-I的对象检测网络在数据中心CPU上获得了类似或更高的映射，并且在数据中心CPU上的fps高达33％。

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.

基于自我注意力的模型，例如视觉变压器（VIT），已经成为计算机视觉中卷积神经网络（CNN）的一种非常有竞争力的建筑。尽管越来越高的变体具有更高的识别精度，但由于自我注意力的二次复杂性，现有的VIT通常在计算和模型大小中要求。尽管已重新引入了最近的CNN的几种成功设计选择（例如，卷积和分层多阶段结构）已重新引入最近的VIT，但它们仍然不足以满足移动设备的有限资源要求。这激发了最近根据最先进的Mobilenet-V2开发光线的尝试，但仍然留下了性能差距。在这项工作中，在这个研究不足的方向上进一步推动了Edgevits，这是一个新的轻巧vits家族，这首先使基于注意力的视觉模型能够与最佳轻巧的CNN竞争，这准确性和设备效率。这是通过基于自我注意力和卷积的最佳整合而引入高度成本效益的本地 - 全球局（LGL）信息交换瓶颈来实现的。对于设备青年的评估，我们不再依赖诸如拖船或参数的不准确代理，而是采用一种实用的方法来直接专注于设备延迟，以及首次首次提供能源效率。具体而言，我们表明，当考虑准确性的延迟和准确性 - 能量折衷时，我们的模型是帕累托最佳的，在几乎所有情况下都严格占据了其他VIT并与最有效的CNN竞争的严格优势。代码可从https://github.com/saic-fi/edgevit获得。

This paper presents X3D, a family of efficient video networks that progressively expand a tiny 2D image classification architecture along multiple network axes, in space, time, width and depth. Inspired by feature selection methods in machine learning, a simple stepwise network expansion approach is employed that expands a single axis in each step, such that good accuracy to complexity trade-off is achieved. To expand X3D to a specific target complexity, we perform progressive forward expansion followed by backward contraction. X3D achieves state-of-the-art performance while requiring 4.8× and 5.5× fewer multiply-adds and parameters for similar accuracy as previous work. Our most surprising finding is that networks with high spatiotemporal resolution can perform well, while being extremely light in terms of network width and parameters. We report competitive accuracy at unprecedented efficiency on video classification and detection benchmarks. Code will be available at: https: //github.com/facebookresearch/SlowFast.

Light-weight convolutional neural networks (CNNs) suffer performance degradation as their low computational budgets constrain both the depth (number of convolution layers) and the width (number of channels) of CNNs, resulting in limited representation capability. To address this issue, we present Dynamic Convolution, a new design that increases model complexity without increasing the network depth or width. Instead of using a single convolution kernel per layer, dynamic convolution aggregates multiple parallel convolution kernels dynamically based upon their attentions, which are input dependent. Assembling multiple kernels is not only computationally efficient due to the small kernel size, but also has more representation power since these kernels are aggregated in a non-linear way via attention. By simply using dynamic convolution for the state-ofthe-art architecture MobileNetV3-Small, the top-1 accuracy of ImageNet classification is boosted by 2.9% with only 4% additional FLOPs and 2.9 AP gain is achieved on COCO keypoint detection.

Semantic segmentation works on the computer vision algorithm for assigning each pixel of an image into a class. The task of semantic segmentation should be performed with both accuracy and efficiency. Most of the existing deep FCNs yield to heavy computations and these networks are very power hungry, unsuitable for real-time applications on portable devices. This project analyzes current semantic segmentation models to explore the feasibility of applying these models for emergency response during catastrophic events. We compare the performance of real-time semantic segmentation models with non-real-time counterparts constrained by aerial images under oppositional settings. Furthermore, we train several models on the Flood-Net dataset, containing UAV images captured after Hurricane Harvey, and benchmark their execution on special classes such as flooded buildings vs. non-flooded buildings or flooded roads vs. non-flooded roads. In this project, we developed a real-time UNet based model and deployed that network on Jetson AGX Xavier module.