Much of the recent progress made in image classification research can be credited to training procedure refinements, such as changes in data augmentations and optimization methods. In the literature, however, most refinements are either briefly mentioned as implementation details or only visible in source code. In this paper, we will examine a collection of such refinements and empirically evaluate their impact on the final model accuracy through ablation study. We will show that, by combining these refinements together, we are able to improve various CNN models significantly. For example, we raise ResNet-50's top-1 validation accuracy from 75.3% to 79.29% on ImageNet. We will also demonstrate that improvement on image classification accuracy leads to better transfer learning performance in other application domains such as object detection and semantic segmentation.

在实现最先进的性能和在实际应用中负担得起的大型模型之间，计算机视觉的差异越来越大。在本文中，我们解决了这个问题，并显着弥合了这两种模型之间的差距。在我们的实证研究中，我们不一定要提出一种新方法，而是要努力确定一个可靠的有效食谱，以使最先进的大型模型在实践中负担得起。我们证明，当正确执行时，知识蒸馏可以成为减少大型尺寸而不损害其性能的强大工具。特别是，我们发现存在某些隐式设计选择，这可能会严重影响蒸馏的有效性。我们的关键贡献是对这些设计选择的明确识别，这些选择以前在文献中尚未阐明。我们通过一项全面的实证研究备份了我们的发现，在广泛的视觉数据集上展示了令人信服的结果，尤其是获得了最先进的Imagenet Resnet-50模型，该模型可实现82.8％的Top-1准确性。 。

We introduce Bootstrap Your Own Latent (BYOL), a new approach to self-supervised image representation learning. BYOL relies on two neural networks, referred to as online and target networks, that interact and learn from each other. From an augmented view of an image, we train the online network to predict the target network representation of the same image under a different augmented view. At the same time, we update the target network with a slow-moving average of the online network. While state-of-the art methods rely on negative pairs, BYOL achieves a new state of the art without them. BYOL reaches 74.3% top-1 classification accuracy on ImageNet using a linear evaluation with a ResNet-50 architecture and 79.6% with a larger ResNet. We show that BYOL performs on par or better than the current state of the art on both transfer and semi-supervised benchmarks. Our implementation and pretrained models are given on GitHub. 3 * Equal contribution; the order of first authors was randomly selected.

The success of deep learning in vision can be attributed to: (a) models with high capacity; (b) increased computational power; and (c) availability of large-scale labeled data. Since 2012, there have been significant advances in representation capabilities of the models and computational capabilities of GPUs. But the size of the biggest dataset has surprisingly remained constant. What will happen if we increase the dataset size by 10× or 100×? This paper takes a step towards clearing the clouds of mystery surrounding the relationship between 'enormous data' and visual deep learning. By exploiting the JFT-300M dataset which has more than 375M noisy labels for 300M images, we investigate how the performance of current vision tasks would change if this data was used for representation learning. Our paper delivers some surprising (and some expected) findings. First, we find that the performance on vision tasks increases logarithmically based on volume of training data size. Second, we show that representation learning (or pretraining) still holds a lot of promise. One can improve performance on many vision tasks by just training a better base model. Finally, as expected, we present new state-of-theart results for different vision tasks including image classification, object detection, semantic segmentation and human pose estimation. Our sincere hope is that this inspires vision community to not undervalue the data and develop collective efforts in building larger datasets.

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.

We introduce submodel co-training, a regularization method related to co-training, self-distillation and stochastic depth. Given a neural network to be trained, for each sample we implicitly instantiate two altered networks, ``submodels'', with stochastic depth: we activate only a subset of the layers. Each network serves as a soft teacher to the other, by providing a loss that complements the regular loss provided by the one-hot label. Our approach, dubbed cosub, uses a single set of weights, and does not involve a pre-trained external model or temporal averaging. Experimentally, we show that submodel co-training is effective to train backbones for recognition tasks such as image classification and semantic segmentation. Our approach is compatible with multiple architectures, including RegNet, ViT, PiT, XCiT, Swin and ConvNext. Our training strategy improves their results in comparable settings. For instance, a ViT-B pretrained with cosub on ImageNet-21k obtains 87.4% top-1 acc. @448 on ImageNet-val.

深度神经网络的计算能力的巨大要求是他们真实世界应用的主要障碍。许多最近的应用特定集成电路（ASIC）芯片特征专用于神经网络加速的硬件支持。然而，由于ASICS多年来发展，他们不可避免地通过神经结构研究的最新发展出现。例如，变换器网络在许多流行芯片上没有本机支持，因此难以部署。在本文中，我们提出了一系列神经网络的拱门，这些网络唯一由距离Asics的大多数架构有效支持的运营商。当产生弓形网时，通过无标记的块块模型蒸馏以逐步的方式消除较少的普通网络结构，如层归一化和嵌入层，同时同时执行Sub-八比特量化以最大化性能。机器翻译和图像分类任务的经验结果确认我们可以将最新的发发的神经架构转换为快速运行和准确的拱网，准备部署多个大规模生产的ASIC芯片。代码将在https://github.com/megvii-research/arch-et栏中提供。

Jitendra Malik once said, "Supervision is the opium of the AI researcher". Most deep learning techniques heavily rely on extreme amounts of human labels to work effectively. In today's world, the rate of data creation greatly surpasses the rate of data annotation. Full reliance on human annotations is just a temporary means to solve current closed problems in AI. In reality, only a tiny fraction of data is annotated. Annotation Efficient Learning (AEL) is a study of algorithms to train models effectively with fewer annotations. To thrive in AEL environments, we need deep learning techniques that rely less on manual annotations (e.g., image, bounding-box, and per-pixel labels), but learn useful information from unlabeled data. In this thesis, we explore five different techniques for handling AEL.

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。

Regional dropout strategies have been proposed to enhance the performance of convolutional neural network classifiers. They have proved to be effective for guiding the model to attend on less discriminative parts of objects (e.g. leg as opposed to head of a person), thereby letting the network generalize better and have better object localization capabilities. On the other hand, current methods for regional dropout remove informative pixels on training images by overlaying a patch of either black pixels or random noise. Such removal is not desirable because it leads to information loss and inefficiency during training. We therefore propose the CutMix augmentation strategy: patches are cut and pasted among training images where the ground truth labels are also mixed proportionally to the area of the patches. By making efficient use of training pixels and retaining the regularization effect of regional dropout, CutMix consistently outperforms the state-of-the-art augmentation strategies on CI-FAR and ImageNet classification tasks, as well as on the Im-ageNet weakly-supervised localization task. Moreover, unlike previous augmentation methods, our CutMix-trained ImageNet classifier, when used as a pretrained model, results in consistent performance gains in Pascal detection and MS-COCO image captioning benchmarks. We also show that CutMix improves the model robustness against input corruptions and its out-of-distribution detection performances. Source code and pretrained models are available at https://github.com/clovaai/CutMix-PyTorch.

视觉识别的“咆哮20S”开始引入视觉变压器（VITS），这将被取代的Cummnets作为最先进的图像分类模型。另一方面，vanilla vit，当应用于一般计算机视觉任务等对象检测和语义分割时面临困难。它是重新引入多个ConvNet Priors的等级变压器（例如，Swin变压器），使变压器实际上可作为通用视觉骨干网，并在各种视觉任务上展示了显着性能。然而，这种混合方法的有效性仍然在很大程度上归功于变压器的内在优越性，而不是卷积的固有感应偏差。在这项工作中，我们重新审视设计空间并测试纯粹的Convnet可以实现的限制。我们逐渐“现代化”标准Reset朝着视觉变压器的设计设计，并发现几个有助于沿途绩效差异的关键组件。此探索的结果是一个纯粹的ConvNet型号被称为ConvNext。完全由标准的Convnet模块构建，ConvNexts在准确性和可扩展性方面与变压器竞争，实现了87.8％的ImageNet Top-1精度和表现优于COCO检测和ADE20K分割的Swin变压器，同时保持了标准Convnet的简单性和效率。

我们分享了我们最近的发现，以试图培训通用分割网络的各种细胞类型和成像方式。我们的方法建立在广义的U-NET体系结构上，该体系结构允许单独评估每个组件。我们修改了传统的二进制培训目标，以包括三个类以进行直接实例细分。进行了有关培训方案，培训设置，网络骨架和各个模块的详细实验。我们提出的培训方案依次从每个数据集中吸取小匹配，并且在优化步骤之前积累了梯度。我们发现，培训通用网络的关键是所有数据集上的历史监督，并且有必要以公正的方式对每个数据集进行采样。我们的实验还表明，可能存在共同的特征来定义细胞类型和成像方式的细胞边界，这可以允许应用训练有素的模型完全看不见的数据集。一些培训技巧可以进一步提高细分性能，包括交叉渗透损失功能中的班级权重，精心设计的学习率调度程序，较大的图像作物以进行上下文信息以及不平衡类别的其他损失条款。我们还发现，由于它们更可靠的统计估计和更高的语义理解，分割性能可以受益于组规范化层和缺陷的空间金字塔池模块。我们参与了在IEEE国际生物医学成像研讨会（ISBI）2021举行的第六个细胞跟踪挑战（CTC）。我们的方法被评估为在主要曲目的初始提交期间，作为最佳亚军，并在额外的竞争中获得了第三名，以准备摘要出版物。

与常规知识蒸馏（KD）不同，自我KD允许网络在没有额外网络的任何指导的情况下向自身学习知识。本文提议从图像混合物（Mixskd）执行自我KD，将这两种技术集成到统一的框架中。 Mixskd相互蒸馏以图形和概率分布在随机的原始图像和它们的混合图像之间以有意义的方式。因此，它通过对混合图像进行监督信号进行建模来指导网络学习跨图像知识。此外，我们通过汇总多阶段功能图来构建一个自学老师网络，以提供软标签以监督骨干分类器，从而进一步提高自我增强的功效。图像分类和转移学习到对象检测和语义分割的实验表明，混合物KD优于其他最先进的自我KD和数据增强方法。该代码可在https://github.com/winycg/self-kd-lib上找到。

神经网络的宽度很重要，因为增加了宽度，这必然会增加模型容量。但是，网络的性能不会随宽度而线性地提高，并且很快就会饱和。在这种情况下，我们认为，增加网络数量（合奏）的数量比纯粹增加宽度可以实现更好的准确性效率折衷。为了证明这一点，一个大型网络就其参数和正则化组件分为几个小网络。这些小型网络中的每一个都有原始参数的一小部分。然后，我们一起训练这些小型网络，使他们看到相同数据的各种观点，以增加它们的多样性。在此共同培训过程中，网络也可以相互学习。结果，小型网络可以比几乎没有或没有额外参数或拖船的大型网络获得更好的合奏性能，即实现更好的准确性效率折衷。通过并发运行，小型网络还可以比大型推理速度更快。以上所有内容都表明，网络的数量是模型缩放的新维度。我们通过广泛的实验在共同基准上使用8种不同的神经体系结构来验证我们的论点。该代码可在\ url {https://github.com/freeformrobotics/divide-and-co-training}中获得。

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

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％。

We design a family of image classification architectures that optimize the trade-off between accuracy and efficiency in a high-speed regime. Our work exploits recent findings in attention-based architectures, which are competitive on highly parallel processing hardware. We revisit principles from the extensive literature on convolutional neural networks to apply them to transformers, in particular activation maps with decreasing resolutions. We also introduce the attention bias, a new way to integrate positional information in vision transformers.As a result, we propose LeVIT: a hybrid neural network for fast inference image classification. We consider different measures of efficiency on different hardware platforms, so as to best reflect a wide range of application scenarios. Our extensive experiments empirically validate our technical choices and show they are suitable to most architectures. Overall, LeViT significantly outperforms existing convnets and vision transformers with respect to the speed/accuracy tradeoff. For example, at 80% ImageNet top-1 accuracy, LeViT is 5 times faster than EfficientNet on CPU. We release the code at https: //github.com/facebookresearch/LeViT.

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}.

我们介绍Softmax梯度篡改，一种用于修改神经网络后向通过的梯度的技术，以提高其准确性。我们的方法使用基于功率的概率变换来改变预测的概率值，然后将梯度重新计算在后向通过。这种修改导致更平滑的渐变简介，我们在经验和理论上展示。我们对剩余网络进行了转换参数进行了网格搜索。我们证明修改CUMMNET中的软MAX梯度可能导致培训准确性提高，从而增加训练数据的适合，并最大限度地利用神经网络的学习能力。当与标签平滑等正则化技术相结合时，我们获得更好的测试度量和更低的泛化间隙。 Softmax渐变篡改在ImageNet DataSet上的基线上以0.52 \％$ 0.52 \％$ 0.52 \％$ 0.52 \％。我们的方法非常通用，可以跨各种不同的网络架构和数据集使用。

神经网络可以从单个图像中了解视觉世界的内容是什么？虽然它显然不能包含存在的可能对象，场景和照明条件 - 在所有可能的256 ^（3x224x224）224尺寸的方形图像中，它仍然可以在自然图像之前提供强大的。为了分析这一假设，我们通过通过监控掠夺教师的知识蒸馏来制定一种训练神经网络的培训神经网络。有了这个，我们发现上述问题的答案是：“令人惊讶的是，很多”。在定量术语中，我们在CiFar-10/100上找到了94％/ 74％的前1个精度，在想象中，通过将这种方法扩展到音频，84％的语音组合。在广泛的分析中，我们解除了增强，源图像和网络架构的选择，以及在从未见过熊猫的网络中发现“熊猫神经元”。这项工作表明，一个图像可用于推断成千上万的对象类，并激励关于增强和图像的基本相互作用的更新的研究议程。