批量白化是一种通过转换输入特征来加速和稳定训练的技术，以具有零平均（居中）和单位方差（缩放），并且通过去除信道（去相关）之间的线性相关性。在常用的结构中，通过批量归一化经验优化，归一化层出现在卷积和激活功能之间。在批量白化研究中采用相同的结构而无需进一步分析;甚至分析了批次白化的前提，即线性层的输入变白。为了弥补差距，我们提出了一种新的卷积单元，符合该理论，我们的方法通常提高批量美白的性能。此外，我们通过调查特征的等级和相关性来展示原始卷积单元的效率。由于我们的方法是可采用的现成增白模块，我们使用迭代标准化（Iternorm），最先进的美白模块，并在五个图像分类数据集中获得显着提高的性能：CiFar-10，CiFar-100 ，幼崽200-2011，斯坦福狗和想象。值得注意的是，我们验证了我们的方法在使用大型学习率，组大小和迭代号时，提高了白化的稳定性和性能。

Deep residual networks were shown to be able to scale up to thousands of layers and still have improving performance. However, each fraction of a percent of improved accuracy costs nearly doubling the number of layers, and so training very deep residual networks has a problem of diminishing feature reuse, which makes these networks very slow to train. To tackle these problems, in this paper we conduct a detailed experimental study on the architecture of ResNet blocks, based on which we propose a novel architecture where we decrease depth and increase width of residual networks. We call the resulting network structures wide residual networks (WRNs) and show that these are far superior over their commonly used thin and very deep counterparts. For example, we demonstrate that even a simple 16-layer-deep wide residual network outperforms in accuracy and efficiency all previous deep residual networks, including thousand-layerdeep networks, achieving new state-of-the-art results on CIFAR, SVHN, COCO, and significant improvements on ImageNet. Our code and models are available at https: //github.com/szagoruyko/wide-residual-networks.

非本地（NL）块是一个流行的模块，它展示了模拟全局上下文的功能。但是，NL块通常具有沉重的计算和记忆成本，因此将块应用于高分辨率特征图是不切实际的。在本文中，为了研究NL块的功效，我们经验分析了输入特征向量的大小和方向是否正确影响向量之间的注意力。结果表明，SoftMax操作的效率低下，该操作通常用于将NL块的注意力图归一化。通过软磁性操作归一化的注意力图极大地依赖于关键向量的大小，并且如果删除幅度信息，则性能将退化。通过用缩放系数替换SoftMax操作，我们证明了CIFAR-10，CIFAR-100和TININE-IMAGENET的性能提高。此外，我们的方法显示了嵌入通道减少和嵌入重量初始化的鲁棒性。值得注意的是，我们的方法在没有额外的计算成本的情况下使多头注意力可用。

分批归一化（BN）由归一化组成部分，然后是仿射转化，并且对于训练深神经网络至关重要。网络中每个BN的标准初始化分别设置了仿射变换量表，并将其转移到1和0。但是，经过训练，我们观察到这些参数从初始化中并没有太大变化。此外，我们注意到归一化过程仍然可以产生过多的值，这对于训练是不可能的。我们重新审视BN公式，并为BN提出了一种新的初始化方法和更新方法，以解决上述问题。实验旨在强调和证明适当的BN规模初始化对性能的积极影响，并使用严格的统计显着性测试进行评估。该方法可以与现有实施方式一起使用，没有额外的计算成本。源代码可在https://github.com/osu-cvl/revisiting-bninit上获得。

Low-rankness plays an important role in traditional machine learning, but is not so popular in deep learning. Most previous low-rank network compression methods compress the networks by approximating pre-trained models and re-training. However, the optimal solution in the Euclidean space may be quite different from the one in the low-rank manifold. A well-pre-trained model is not a good initialization for the model with low-rank constraints. Thus, the performance of a low-rank compressed network degrades significantly. Compared to other network compression methods such as pruning, low-rank methods attracts less attention in recent years. In this paper, we devise a new training method, low-rank projection with energy transfer (LRPET), that trains low-rank compressed networks from scratch and achieves competitive performance. First, we propose to alternately perform stochastic gradient descent training and projection onto the low-rank manifold. Compared to re-training on the compact model, this enables full utilization of model capacity since solution space is relaxed back to Euclidean space after projection. Second, the matrix energy (the sum of squares of singular values) reduction caused by projection is compensated by energy transfer. We uniformly transfer the energy of the pruned singular values to the remaining ones. We theoretically show that energy transfer eases the trend of gradient vanishing caused by projection. Third, we propose batch normalization (BN) rectification to cut off its effect on the optimal low-rank approximation of the weight matrix, which further improves the performance. Comprehensive experiments on CIFAR-10 and ImageNet have justified that our method is superior to other low-rank compression methods and also outperforms recent state-of-the-art pruning methods. Our code is available at https://github.com/BZQLin/LRPET.

灵感来自动物视觉系统中的两个基本机制，我们介绍了一种特征变换技术，在深神经网络训练中强加不变性。生成的算法需要较少的参数调整，用初始学习速率1.0提供良好的列车，并且容易地推广到不同的任务。我们使用数据中的本地统计数据强制不变性，以使类似的样本对齐不同的标度。为了加速融合，我们强制使用从批处理中提取的全局统计数据来执行GL（n）-invariance属性，使得梯度下降溶液应保持不变的基础变化。分析分析表明我们所提出的修改需要底层卷积层的计算的5％。在卷积网络和变压器网络上测试，我们提出的技术需要较少的迭代训练，超过所有基线，通过大幅度，无缝工作，对小型和大批量训练，并适用于不同的计算机视觉和语言任务。

标准化技术已成为现代卷积神经网络（Convnets）中的基本组件。特别是，许多最近的作品表明，促进重量的正交性有助于培训深层模型并提高鲁棒性。对于Courmnets，大多数现有方法基于惩罚或归一化矩阵判断或施加卷积核的重量矩阵。这些方法经常摧毁或忽视核的良性卷积结构;因此，对于深扫描器来说，它们通常是昂贵或不切实际的。相比之下，我们介绍了一种简单富有高效的“卷积归一化”（ConvNORM）方法，可以充分利用傅立叶域中的卷积结构，并用作简单的即插即用模块，以方便地结合到任何围栏中。我们的方法是通过最近关于卷积稀疏编码的预处理方法的工作启发，可以有效地促进每个层的频道方向等距。此外，我们表明我们的判断可以降低重量矩阵的层状频谱标准，从而改善网络的嘴唇，导致培训更容易培训和改善深扫描器的鲁棒性。在噪声损坏和生成的对抗网络（GAN）下应用于分类，我们表明CONVNOMOL提高了常见扫描仪（如RENET和GAN性能）的稳健性。我们通过Cifar和Imagenet的数值实验验证了我们的研究结果。

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.

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.

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。

已经提出了各种归一化层来帮助培训神经网络。组归一化（GN）是在视觉识别任务中实现出色表现的有效和有吸引力的研究之一。尽管取得了巨大的成功，但GN仍然存在几个问题，可能会对神经网络培训产生负面影响。在本文中，我们介绍了一个分析框架，并讨论了GN在影响神经网络训练过程时的工作原理。从实验结果中，我们得出结论GN对批处理标准化（BN）的较低性能的真正原因：1）\ TextBf {不稳定的训练性能}，2）\ TextBf {更敏感}对失真，无论是来自外部噪声还是扰动。通过正规化。此外，我们发现GN只能在某个特定时期内帮助神经网络培训，而BN可以帮助整个培训中的网络。为了解决这些问题，我们提出了一个新的归一化层，该层是通过合并BN的优势在GN顶部构建的。图像分类任务的实验结果表明，所提出的归一化层优于官方GN，以提高识别精度，无论批次大小如何，并稳定网络训练。

本文介绍了一种新颖的卷积方法，称为生成卷积（GCONV），这对于改善生成的对抗网络（GaN）性能来说是简单而有效的。与标准卷积不同，GCONV首先选择与给定的潜像兼容的有用内核，然后线性地将所选内核结合起来制作潜在特定的内核。使用潜在特定的内核，所提出的方法产生潜在特定的特征，鼓励发电机产生高质量的图像。这种方法很简单，但令人惊讶地有效。首先，GaN性能随着额外的硬件成本而显着提高。其次，GCONV可以用于现有的最先进的发电机而不修改网络架构。为了揭示GCONV的优越性，本文使用各种标准数据集提供了广泛的实验，包括CiFar-10，CiFar-100，Lsun-Church，Celeba和微小想象成。定量评估证明，GCONV在成立得分（IS）和FRECHET成立距离（FID）方面大大提高了无条件和条件GAN的性能。例如，所提出的方法改善了FID，分别从35.13到29.76和20.23到22.64的微小想象网数据集上的分数。

神经架构的创新促进了语言建模和计算机视觉中的重大突破。不幸的是，如果网络参数未正确初始化，新颖的架构通常会导致挑战超参数选择和培训不稳定。已经提出了许多架构特定的初始化方案，但这些方案并不总是可移植到新体系结构。本文介绍了毕业，一种用于初始化神经网络的自动化和架构不可知论由方法。毕业基础是一个简单的启发式;调整每个网络层的规范，使得具有规定的超参数的SGD或ADAM的单个步骤导致可能的损耗值最小。通过在每个参数块前面引入标量乘数变量，然后使用简单的数字方案优化这些变量来完成此调整。 GradInit加速了许多卷积架构的收敛性和测试性能，无论是否有跳过连接，甚至没有归一化层。它还提高了机器翻译的原始变压器架构的稳定性，使得在广泛的学习速率和动量系数下使用ADAM或SGD来训练它而无需学习速率预热。代码可在https://github.com/zhuchen03/gradinit上获得。

我们研究了使用尖刺，现场依赖的随机矩阵理论研究迷你批次对深神经网络损失景观的影响。我们表明，批量黑森州的极值值的大小大于经验丰富的黑森州。我们还获得了类似的结果对Hessian的概括高斯牛顿矩阵近似。由于我们的定理，我们推导出作为批量大小的最大学习速率的分析表达式，为随机梯度下降（线性缩放）和自适应算法（例如ADAM（Square Root Scaling）提供了通知实际培训方案，例如光滑，非凸深神经网络。虽然随机梯度下降的线性缩放是在我们概括的更多限制性条件下导出的，但是适应优化者的平方根缩放规则是我们的知识，完全小说。随机二阶方法和自适应方法的百分比，我们得出了最小阻尼系数与学习率与批量尺寸的比率成比例。我们在Cifar-$ 100 $和ImageNet数据集上验证了我们的VGG / WimerEsnet架构上的索赔。根据我们对象检的调查，我们基于飞行学习率和动量学习者开发了一个随机兰齐齐竞争，这避免了对这些关键的超参数进行昂贵的多重评估的需求，并在预残留的情况下显示出良好的初步结果Cifar的architecure - $ 100 $。

Structural pruning of neural network parameters reduces computation, energy, and memory transfer costs during inference. We propose a novel method that estimates the contribution of a neuron (filter) to the final loss and iteratively removes those with smaller scores. We describe two variations of our method using the first and secondorder Taylor expansions to approximate a filter's contribution. Both methods scale consistently across any network layer without requiring per-layer sensitivity analysis and can be applied to any kind of layer, including skip connections. For modern networks trained on ImageNet, we measured experimentally a high (>93%) correlation between the contribution computed by our methods and a reliable estimate of the true importance. Pruning with the proposed methods leads to an improvement over state-ofthe-art in terms of accuracy, FLOPs, and parameter reduction. On ResNet-101, we achieve a 40% FLOPS reduction by removing 30% of the parameters, with a loss of 0.02% in the top-1 accuracy on ImageNet. Code is available at https://github.com/NVlabs/Taylor_pruning.

In this work, we propose "Residual Attention Network", a convolutional neural network using attention mechanism which can incorporate with state-of-art feed forward network architecture in an end-to-end training fashion. Our Residual Attention Network is built by stacking Attention Modules which generate attention-aware features. The attention-aware features from different modules change adaptively as layers going deeper. Inside each Attention Module, bottom-up top-down feedforward structure is used to unfold the feedforward and feedback attention process into a single feedforward process. Importantly, we propose attention residual learning to train very deep Residual Attention Networks which can be easily scaled up to hundreds of layers.Extensive analyses are conducted on CIFAR-10 and CIFAR-100 datasets to verify the effectiveness of every module mentioned above. Our Residual Attention Network achieves state-of-the-art object recognition performance on three benchmark datasets including CIFAR-10 (3.90% error), CIFAR-100 (20.45% error) and ImageNet (4.8% single model and single crop, top-5 error). Note that, our method achieves 0.6% top-1 accuracy improvement with 46% trunk depth and 69% forward FLOPs comparing to ResNet-200. The experiment also demonstrates that our network is robust against noisy labels.

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。

网络压缩对于使深网的效率更高，更快且可推广到低端硬件至关重要。当前的网络压缩方法有两个开放问题：首先，缺乏理论框架来估计最大压缩率；其次，有些层可能会过多地进行，从而导致网络性能大幅下降。为了解决这两个问题，这项研究提出了一种基于梯度矩阵分析方法，以估计最大网络冗余。在最大速率的指导下，开发了一种新颖而有效的层次网络修剪算法，以最大程度地凝结神经元网络结构而无需牺牲网络性能。进行实质性实验以证明新方法修剪几个高级卷积神经网络（CNN）体系结构的功效。与现有的修剪方法相比，拟议的修剪算法实现了最先进的性能。与其他方法相比，在相同或相似的压缩比下，新方法提供了最高的网络预测准确性。

深度学习归一化技术的基本特性，例如批准归一化，正在使范围前的参数量表不变。此类参数的固有域是单位球，因此可以通过球形优化的梯度优化动力学以不同的有效学习率（ELR）来表示，这是先前研究的。在这项工作中，我们使用固定的ELR直接研究了训练量表不变的神经网络的特性。我们根据ELR值发现了这种训练的三个方案：收敛，混乱平衡和差异。我们详细研究了这些制度示例的理论检查，以及对真实规模不变深度学习模型的彻底经验分析。每个制度都有独特的特征，并反映了内在损失格局的特定特性，其中一些与先前对常规和规模不变的神经网络培训的研究相似。最后，我们证明了如何在归一化网络的常规培训以及如何利用它们以实现更好的Optima中反映发现的制度。

We introduce the "exponential linear unit" (ELU) which speeds up learning in deep neural networks and leads to higher classification accuracies. Like rectified linear units (ReLUs), leaky ReLUs (LReLUs) and parametrized ReLUs (PRe-LUs), ELUs alleviate the vanishing gradient problem via the identity for positive values. However ELUs have improved learning characteristics compared to the units with other activation functions. In contrast to ReLUs, ELUs have negative values which allows them to push mean unit activations closer to zero like batch normalization but with lower computational complexity. Mean shifts toward zero speed up learning by bringing the normal gradient closer to the unit natural gradient because of a reduced bias shift effect. While LReLUs and PReLUs have negative values, too, they do not ensure a noise-robust deactivation state. ELUs saturate to a negative value with smaller inputs and thereby decrease the forward propagated variation and information. Therefore ELUs code the degree of presence of particular phenomena in the input, while they do not quantitatively model the degree of their absence. In experiments, ELUs lead not only to faster learning, but also to significantly better generalization performance than ReLUs and LReLUs on networks with more than 5 layers. On CIFAR-100 ELUs networks significantly outperform ReLU networks with batch normalization while batch normalization does not improve ELU networks. ELU networks are among the top 10 reported CIFAR-10 results and yield the best published result on CIFAR-100, without resorting to multi-view evaluation or model averaging. On ImageNet, ELU networks considerably speed up learning compared to a ReLU network with the same architecture, obtaining less than 10% classification error for a single crop, single model network.