在这项工作中，我们建议内核过滤线性过度参数化（KFLO），其中在训练过程中使用了线性过滤层的线性级联，以提高测试时间的网络性能。我们以内核过滤的方式实施了这一级联反应，从而防止训练有素的建筑变得更加深入。这也允许使用我们的方法几乎与任何网络体系结构一起使用，并在测试时间将过滤层组合到单层中。因此，我们的方法在推断过程中不会增加计算复杂性。我们证明了KFLO在各种网络模型和数据集中的优势在监督学习中。

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。

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.

Despite the fact that deep neural networks are powerful models and achieve appealing results on many tasks, they are too large to be deployed on edge devices like smartphones or embedded sensor nodes. There have been efforts to compress these networks, and a popular method is knowledge distillation, where a large (teacher) pre-trained network is used to train a smaller (student) network. However, in this paper, we show that the student network performance degrades when the gap between student and teacher is large. Given a fixed student network, one cannot employ an arbitrarily large teacher, or in other words, a teacher can effectively transfer its knowledge to students up to a certain size, not smaller. To alleviate this shortcoming, we introduce multi-step knowledge distillation, which employs an intermediate-sized network (teacher assistant) to bridge the gap between the student and the teacher. Moreover, we study the effect of teacher assistant size and extend the framework to multi-step distillation. Theoretical analysis and extensive experiments on CIFAR-10,100 and ImageNet datasets and on CNN and ResNet architectures substantiate the effectiveness of our proposed approach.

Transferring knowledge from a teacher neural network pretrained on the same or a similar task to a student neural network can significantly improve the performance of the student neural network. Existing knowledge transfer approaches match the activations or the corresponding handcrafted features of the teacher and the student networks. We propose an information-theoretic framework for knowledge transfer which formulates knowledge transfer as maximizing the mutual information between the teacher and the student networks. We compare our method with existing knowledge transfer methods on both knowledge distillation and transfer learning tasks and show that our method consistently outperforms existing methods. We further demonstrate the strength of our method on knowledge transfer across heterogeneous network architectures by transferring knowledge from a convolutional neural network (CNN) to a multi-layer perceptron (MLP) on CIFAR-10. The resulting MLP significantly outperforms the-state-of-the-art methods and it achieves similar performance to the CNN with a single convolutional layer. * Contributed during an internship at Amazon.

While depth tends to improve network performances, it also makes gradient-based training more difficult since deeper networks tend to be more non-linear. The recently proposed knowledge distillation approach is aimed at obtaining small and fast-to-execute models, and it has shown that a student network could imitate the soft output of a larger teacher network or ensemble of networks. In this paper, we extend this idea to allow the training of a student that is deeper and thinner than the teacher, using not only the outputs but also the intermediate representations learned by the teacher as hints to improve the training process and final performance of the student. Because the student intermediate hidden layer will generally be smaller than the teacher's intermediate hidden layer, additional parameters are introduced to map the student hidden layer to the prediction of the teacher hidden layer. This allows one to train deeper students that can generalize better or run faster, a trade-off that is controlled by the chosen student capacity. For example, on CIFAR-10, a deep student network with almost 10.4 times less parameters outperforms a larger, state-of-the-art teacher network.

Attention plays a critical role in human visual experience. Furthermore, it has recently been demonstrated that attention can also play an important role in the context of applying artificial neural networks to a variety of tasks from fields such as computer vision and NLP. In this work we show that, by properly defining attention for convolutional neural networks, we can actually use this type of information in order to significantly improve the performance of a student CNN network by forcing it to mimic the attention maps of a powerful teacher network.To that end, we propose several novel methods of transferring attention, showing consistent improvement across a variety of datasets and convolutional neural network architectures. Code and models for our experiments are available at https://github.com/szagoruyko/attention-transfer.

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.

We introduce a novel technique for knowledge transfer, where knowledge from a pretrained deep neural network (DNN) is distilled and transferred to another DNN. As the DNN maps from the input space to the output space through many layers sequentially, we define the distilled knowledge to be transferred in terms of flow between layers, which is calculated by computing the inner product between features from two layers. When we compare the student DNN and the original network with the same size as the student DNN but trained without a teacher network, the proposed method of transferring the distilled knowledge as the flow between two layers exhibits three important phenomena: (1) the student DNN that learns the distilled knowledge is optimized much faster than the original model; (2) the student DNN outperforms the original DNN; and (3) the student DNN can learn the distilled knowledge from a teacher DNN that is trained at a different task, and the student DNN outperforms the original DNN that is trained from scratch.

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.

Recent work has shown that convolutional networks can be substantially deeper, more accurate, and efficient to train if they contain shorter connections between layers close to the input and those close to the output. In this paper, we embrace this observation and introduce the Dense Convolutional Network (DenseNet), which connects each layer to every other layer in a feed-forward fashion. Whereas traditional convolutional networks with L layers have L connections-one between each layer and its subsequent layer-our network has L(L+1) 2 direct connections. For each layer, the feature-maps of all preceding layers are used as inputs, and its own feature-maps are used as inputs into all subsequent layers. DenseNets have several compelling advantages: they alleviate the vanishing-gradient problem, strengthen feature propagation, encourage feature reuse, and substantially reduce the number of parameters. We evaluate our proposed architecture on four highly competitive object recognition benchmark tasks SVHN, and ImageNet). DenseNets obtain significant improvements over the state-of-the-art on most of them, whilst requiring less computation to achieve high performance. Code and pre-trained models are available at https://github.com/liuzhuang13/DenseNet.

在这项工作中，我们提出了相互信息最大化知识蒸馏（MIMKD）。我们的方法使用对比目标来同时估计，并最大化教师和学生网络之间的本地和全球特征表示的相互信息的下限。我们通过广泛的实验证明，这可以通过将知识从更加性能但计算昂贵的模型转移来改善低容量模型的性能。这可用于产生更好的模型，可以在具有低计算资源的设备上运行。我们的方法灵活，我们可以将具有任意网络架构的教师蒸馏到任意学生网络。我们的经验结果表明，MIMKD优于各种学生教师对的竞争方法，具有不同的架构，以及学生网络的容量极低。我们能够通过从Reset-50蒸馏出来的知识，从基线精度为Shufflenetv2获得74.55％的精度。在Imagenet上，我们使用Reset-34教师网络将Reset-18网络从68.88％提高到70.32％的准确度（1.44％+）。

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。

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。

由于它们的时间加工能力及其低交换（尺寸，重量和功率）以及神经形态硬件中的节能实现，尖峰神经网络（SNNS）已成为传统人工神经网络（ANN）的有趣替代方案。然而，培训SNNS所涉及的挑战在准确性方面有限制了它们的表现，从而限制了他们的应用。因此，改善更准确的特征提取的学习算法和神经架构是SNN研究中的当前优先级之一。在本文中，我们展示了现代尖峰架构的关键组成部分的研究。我们在从最佳执行网络中凭经验比较了图像分类数据集中的不同技术。我们设计了成功的残余网络（Reset）架构的尖峰版本，并测试了不同的组件和培训策略。我们的结果提供了SNN设计的最新版本，它允许在尝试构建最佳视觉特征提取器时进行明智的选择。最后，我们的网络优于CIFAR-10（94.1％）和CIFAR-100（74.5％）数据集的先前SNN架构，并将现有技术与DVS-CIFAR10（71.3％）相匹配，参数较少而不是先前的状态艺术，无需安静转换。代码在https://github.com/vicenteax/spiking_resnet上获得。

The success of CNNs in various applications is accompanied by a significant increase in the computation and parameter storage costs. Recent efforts toward reducing these overheads involve pruning and compressing the weights of various layers without hurting original accuracy. However, magnitude-based pruning of weights reduces a significant number of parameters from the fully connected layers and may not adequately reduce the computation costs in the convolutional layers due to irregular sparsity in the pruned networks. We present an acceleration method for CNNs, where we prune filters from CNNs that are identified as having a small effect on the output accuracy. By removing whole filters in the network together with their connecting feature maps, the computation costs are reduced significantly. In contrast to pruning weights, this approach does not result in sparse connectivity patterns. Hence, it does not need the support of sparse convolution libraries and can work with existing efficient BLAS libraries for dense matrix multiplications. We show that even simple filter pruning techniques can reduce inference costs for VGG-16 by up to 34% and ResNet-110 by up to 38% on CIFAR10 while regaining close to the original accuracy by retraining the networks.

知识蒸馏（KD）可以有效地将知识从繁琐的网络（教师）转移到紧凑的网络（学生），在某些计算机视觉应用中证明了其优势。知识的表示对于知识转移和学生学习至关重要，这通常以手工制作的方式定义或直接使用中间功能。在本文中，我们建议在教师学生架构下为单像超级分辨率任务提出一种模型 - 不足的元知识蒸馏方法。它提供了一种更灵活，更准确的方法，可以通过知识代表网络（KRNET）的能力来帮助教师通过具有可学习参数的知识传输知识。为了提高知识表示对学生需求的看法能力，我们建议通过采用学生特征以及KRNET中的教师和学生之间的相关性来解决从中间产出到转移知识的转型过程。具体而言，生成纹理感知的动态内核，然后提取要改进的纹理特征，并将相应的教师指导分解为质地监督，以进一步促进高频细节的恢复质量。此外，KRNET以元学习方式进行了优化，以确保知识转移和学生学习有益于提高学生的重建质量。在各种单个图像超分辨率数据集上进行的实验表明，我们所提出的方法优于现有的定义知识表示相关的蒸馏方法，并且可以帮助超分辨率算法实现更好的重建质量，而无需引入任何推理复杂性。

Computational units in artificial neural networks follow a simplified model of biological neurons. In the biological model, the output signal of a neuron runs down the axon, splits following the many branches at its end, and passes identically to all the downward neurons of the network. Each of the downward neurons will use their copy of this signal as one of many inputs dendrites, integrate them all and fire an output, if above some threshold. In the artificial neural network, this translates to the fact that the nonlinear filtering of the signal is performed in the upward neuron, meaning that in practice the same activation is shared between all the downward neurons that use that signal as their input. Dendrites thus play a passive role. We propose a slightly more complex model for the biological neuron, where dendrites play an active role: the activation in the output of the upward neuron becomes optional, and instead the signals going through each dendrite undergo independent nonlinear filterings, before the linear combination. We implement this new model into a ReLU computational unit and discuss its biological plausibility. We compare this new computational unit with the standard one and describe it from a geometrical point of view. We provide a Keras implementation of this unit into fully connected and convolutional layers and estimate their FLOPs and weights change. We then use these layers in ResNet architectures on CIFAR-10, CIFAR-100, Imagenette, and Imagewoof, obtaining performance improvements over standard ResNets up to 1.73%. Finally, we prove a universal representation theorem for continuous functions on compact sets and show that this new unit has more representational power than its standard counterpart.

机器学习中的知识蒸馏是将知识从名为教师的大型模型转移到一个名为“学生”的较小模型的过程。知识蒸馏是将大型网络（教师）压缩到较小网络（学生）的技术之一，该网络可以部署在手机等小型设备中。当教师和学生之间的网络规模差距增加时，学生网络的表现就会下降。为了解决这个问题，在教师模型和名为助教模型的学生模型之间采用了中间模型，这反过来弥补了教师与学生之间的差距。在这项研究中，我们已经表明，使用多个助教模型，可以进一步改进学生模型（较小的模型）。我们使用加权集合学习将这些多个助教模型组合在一起，我们使用了差异评估优化算法来生成权重值。

Very deep convolutional networks with hundreds of layers have led to significant reductions in error on competitive benchmarks. Although the unmatched expressiveness of the many layers can be highly desirable at test time, training very deep networks comes with its own set of challenges. The gradients can vanish, the forward flow often diminishes, and the training time can be painfully slow. To address these problems, we propose stochastic depth, a training procedure that enables the seemingly contradictory setup to train short networks and use deep networks at test time. We start with very deep networks but during training, for each mini-batch, randomly drop a subset of layers and bypass them with the identity function. This simple approach complements the recent success of residual networks. It reduces training time substantially and improves the test error significantly on almost all data sets that we used for evaluation. With stochastic depth we can increase the depth of residual networks even beyond 1200 layers and still yield meaningful improvements in test error (4.91% on CIFAR-10).