This paper does not describe a novel method. Instead, it studies a straightforward, incremental, yet must-know baseline given the recent progress in computer vision: selfsupervised learning for Vision Transformers (ViT). While the training recipes for standard convolutional networks have been highly mature and robust, the recipes for ViT are yet to be built, especially in the self-supervised scenarios where training becomes more challenging. In this work, we go back to basics and investigate the effects of several fundamental components for training self-supervised ViT. We observe that instability is a major issue that degrades accuracy, and it can be hidden by apparently good results. We reveal that these results are indeed partial failure, and they can be improved when training is made more stable. We benchmark ViT results in MoCo v3 and several other selfsupervised frameworks, with ablations in various aspects. We discuss the currently positive evidence as well as challenges and open questions. We hope that this work will provide useful data points and experience for future research.

本文显示屏蔽的自动化器（MAE）是可扩展的自我监督学习者，用于计算机愿景。我们的MAE方法很简单：我们掩盖输入图像的随机补丁并重建缺失像素。它基于两个核心设计。首先，我们开发一个不对称的编码器解码器架构，其中编码器仅在掩码的可见子集（没有掩码令牌）上，以及重量解码器，该重量解码器从潜像和掩码令牌重建原始图像。其次，我们发现掩蔽了高比例的输入图像，例如，75％，产生非凡和有意义的自我监督任务。耦合这两种设计使我们能够有效且有效地培训大型模型：我们加速培训（3倍或更多）并提高准确性。我们可扩展的方法允许学习概括的高容量模型：例如，Vanilla Vit-Maxim模型在使用Imagenet-1K数据的方法中实现最佳准确性（87.8％）。下游任务中的转移性能优于监督预培训并显示有前途的缩放行为。

Siamese networks have become a common structure in various recent models for unsupervised visual representation learning. These models maximize the similarity between two augmentations of one image, subject to certain conditions for avoiding collapsing solutions. In this paper, we report surprising empirical results that simple Siamese networks can learn meaningful representations even using none of the following: (i) negative sample pairs, (ii) large batches, (iii) momentum encoders. Our experiments show that collapsing solutions do exist for the loss and structure, but a stop-gradient operation plays an essential role in preventing collapsing. We provide a hypothesis on the implication of stop-gradient, and further show proof-of-concept experiments verifying it. Our "SimSiam" method achieves competitive results on ImageNet and downstream tasks. We hope this simple baseline will motivate people to rethink the roles of Siamese architectures for unsupervised representation learning. Code will be made available.

We present Momentum Contrast (MoCo) for unsupervised visual representation learning. From a perspective on contrastive learning [29] as dictionary look-up, we build a dynamic dictionary with a queue and a moving-averaged encoder. This enables building a large and consistent dictionary on-the-fly that facilitates contrastive unsupervised learning. MoCo provides competitive results under the common linear protocol on ImageNet classification. More importantly, the representations learned by MoCo transfer well to downstream tasks. MoCo can outperform its supervised pre-training counterpart in 7 detection/segmentation tasks on PASCAL VOC, COCO, and other datasets, sometimes surpassing it by large margins. This suggests that the gap between unsupervised and supervised representation learning has been largely closed in many vision tasks.

We present Fast Language-Image Pre-training (FLIP), a simple and more efficient method for training CLIP. Our method randomly masks out and removes a large portion of image patches during training. Masking allows us to learn from more image-text pairs given the same wall-clock time and contrast more samples per iteration with similar memory footprint. It leads to a favorable trade-off between accuracy and training time. In our experiments on 400 million image-text pairs, FLIP improves both accuracy and speed over the no-masking baseline. On a large diversity of downstream tasks, FLIP dominantly outperforms the CLIP counterparts trained on the same data. Facilitated by the speedup, we explore the scaling behavior of increasing the model size, data size, or training length, and report encouraging results and comparisons. We hope that our work will foster future research on scaling vision-language learning.

Vision transformer (ViT) models exhibit substandard optimizability. In particular, they are sensitive to the choice of optimizer (AdamW vs. SGD), optimizer hyperparameters, and training schedule length. In comparison, modern convolutional neural networks are easier to optimize. Why is this the case? In this work, we conjecture that the issue lies with the patchify stem of ViT models, which is implemented by a stride-p p×p convolution (p = 16 by default) applied to the input image. This large-kernel plus large-stride convolution runs counter to typical design choices of convolutional layers in neural networks. To test whether this atypical design choice causes an issue, we analyze the optimization behavior of ViT models with their original patchify stem versus a simple counterpart where we replace the ViT stem by a small number of stacked stride-two 3×3 convolutions. While the vast majority of computation in the two ViT designs is identical, we find that this small change in early visual processing results in markedly different training behavior in terms of the sensitivity to optimization settings as well as the final model accuracy. Using a convolutional stem in ViT dramatically increases optimization stability and also improves peak performance (by ∼1-2% top-1 accuracy on ImageNet-1k), while maintaining flops and runtime. The improvement can be observed across the wide spectrum of model complexities (from 1G to 36G flops) and dataset scales (from ImageNet-1k to ImageNet-21k). These findings lead us to recommend using a standard, lightweight convolutional stem for ViT models in this regime as a more robust architectural choice compared to the original ViT model design.

本文研究了两种技术，用于开发有效的自我监督视觉变压器（ESVIT）进行视觉表示学习。首先，我们通过一项全面的实证研究表明，具有稀疏自我生产的多阶段体系结构可以显着降低建模的复杂性，但具有失去捕获图像区域之间细粒度对应关系的能力的成本。其次，我们提出了一项新的区域匹配训练任务，该任务使模型可以捕获细粒的区域依赖性，因此显着提高了学习视觉表示的质量。我们的结果表明，ESVIT在ImageNet线性探针评估上结合两种技术，在ImageNet线性探针评估中获得了81.3％的TOP-1，优于先前的艺术，其较高吞吐量的顺序幅度约为较高。当转移到下游线性分类任务时，ESVIT在18个数据集中的17个中优于其受监督的对方。代码和模型可公开可用：https：//github.com/microsoft/esvit

While the Transformer architecture has become the de-facto standard for natural language processing tasks, its applications to computer vision remain limited. In vision, attention is either applied in conjunction with convolutional networks, or used to replace certain components of convolutional networks while keeping their overall structure in place. We show that this reliance on CNNs is not necessary and a pure transformer applied directly to sequences of image patches can perform very well on image classification tasks. When pre-trained on large amounts of data and transferred to multiple mid-sized or small image recognition benchmarks (ImageNet, CIFAR-100, VTAB, etc.), Vision Transformer (ViT) attains excellent results compared to state-of-the-art convolutional networks while requiring substantially fewer computational resources to train. 1

蒙面图像建模（MIM）在各种视觉任务上取得了令人鼓舞的结果。但是，学到的表示形式的有限可区分性表现出来，使一个更强大的视力学习者还有很多值得一试。为了实现这一目标，我们提出了对比度蒙面的自动编码器（CMAE），这是一种新的自我监督的预训练方法，用于学习更全面和有能力的视觉表示。通过详细统一的对比度学习（CL）和掩盖图像模型（MIM），CMAE利用了它们各自的优势，并以强大的实例可辨别性和局部的可感知来学习表示形式。具体而言，CMAE由两个分支组成，其中在线分支是不对称的编码器编码器，而目标分支是动量更新的编码器。在培训期间，在线编码器从蒙面图像的潜在表示中重建了原始图像，以学习整体特征。馈送完整图像的目标编码器通过其在线学习通过对比度学习增强了功能可区分性。为了使CL与MIM兼容，CMAE引入了两个新组件，即用于生成合理的正视图和特征解码器的像素移位，以补充对比度对的特征。多亏了这些新颖的设计，CMAE可以有效地提高了MIM对应物的表示质量和转移性能。 CMAE在图像分类，语义分割和对象检测的高度竞争基准上实现了最先进的性能。值得注意的是，CMAE-BASE在Imagenet上获得了$ 85.3 \％$ $ TOP-1的准确性和$ 52.5 \％$ MIOU的ADE20K，分别超过了$ 0.7 \％\％$ $和$ 1.8 \％$ $。代码将公开可用。

我们呈现蒙版特征预测（MaskFeat），用于自我监督的视频模型的预训练。我们的方法首先随机地掩盖输入序列的一部分，然后预测蒙面区域的特征。我们研究五种不同类型的功能，找到面向导向渐变（HOG）的直方图，手工制作的特征描述符，在性能和效率方面尤其良好。我们观察到猪中的局部对比标准化对于良好的结果至关重要，这与使用HOG进行视觉识别的早期工作符合。我们的方法可以学习丰富的视觉知识和基于大规模的变压器的模型。在不使用额外的模型重量或监督的情况下，在未标记视频上预先培训的MaskFeat在动力学-400上使用MVIT-L达到86.7％的前所未有的结果，在动力学-600，88.3％上，88.3％，在动力学-700,88.8地图上SSV2上的75.0％。 MaskFeat进一步推广到图像输入，其可以被解释为具有单个帧的视频，并在想象中获得竞争结果。

最近，蒙面图像建模（MIM）在自我监视的视觉识别方面取得了巨大的成功。但是，作为一个基于重建的框架，了解MIM的工作原理仍然是一个悬而未决的问题，因为MIM与以前研究过的暹罗方法（例如对比度学习）有很大不同。在本文中，我们提出了一个新的观点：MIM隐含地学习咬合不变特征，这与其他暹罗方法类似，而后者则学习其他不变性。通过将MIM公式放松为等效的暹罗形式，可以用常规方法在统一框架中解释MIM方法，其中只有a）数据转换，即学习什么不变性，b）相似性测量是不同的。此外，以Mae（He等）为MIM的一个代表性示例，我们从经验上发现MIM模型的成功与选择相似性功能的选择有点联系，但是蒙面图像引入了学习的咬合不变特征 - 事实证明对于视觉变压器来说，这是一个受欢迎的初始化，即使学习的功能可能不太语义。我们希望我们的发现能够激发研究人员在计算机视觉社区中开发更强大的自我监督方法。

Masked image modelling (e.g., Masked AutoEncoder) and contrastive learning (e.g., Momentum Contrast) have shown impressive performance on unsupervised visual representation learning. This work presents Masked Contrastive Representation Learning (MACRL) for self-supervised visual pre-training. In particular, MACRL leverages the effectiveness of both masked image modelling and contrastive learning. We adopt an asymmetric setting for the siamese network (i.e., encoder-decoder structure in both branches), where one branch with higher mask ratio and stronger data augmentation, while the other adopts weaker data corruptions. We optimize a contrastive learning objective based on the learned features from the encoder in both branches. Furthermore, we minimize the $L_1$ reconstruction loss according to the decoders' outputs. In our experiments, MACRL presents superior results on various vision benchmarks, including CIFAR-10, CIFAR-100, Tiny-ImageNet, and two other ImageNet subsets. Our framework provides unified insights on self-supervised visual pre-training and future research.

Driven by improved architectures and better representation learning frameworks, the field of visual recognition has enjoyed rapid modernization and performance boost in the early 2020s. For example, modern ConvNets, represented by ConvNeXt, have demonstrated strong performance in various scenarios. While these models were originally designed for supervised learning with ImageNet labels, they can also potentially benefit from self-supervised learning techniques such as masked autoencoders (MAE). However, we found that simply combining these two approaches leads to subpar performance. In this paper, we propose a fully convolutional masked autoencoder framework and a new Global Response Normalization (GRN) layer that can be added to the ConvNeXt architecture to enhance inter-channel feature competition. This co-design of self-supervised learning techniques and architectural improvement results in a new model family called ConvNeXt V2, which significantly improves the performance of pure ConvNets on various recognition benchmarks, including ImageNet classification, COCO detection, and ADE20K segmentation. We also provide pre-trained ConvNeXt V2 models of various sizes, ranging from an efficient 3.7M-parameter Atto model with 76.7% top-1 accuracy on ImageNet, to a 650M Huge model that achieves a state-of-the-art 88.9% accuracy using only public training data.

我们专注于更好地理解增强不变代表性学习的关键因素。我们重新访问moco v2和byol，并试图证明以下假设的真实性：不同的框架即使具有相同的借口任务也会带来不同特征的表示。我们建立了MoCo V2和BYOL之间公平比较的第一个基准，并观察：（i）复杂的模型配置使得可以更好地适应预训练数据集； （ii）从实现竞争性转移表演中获得的预训练和微调阻碍模型的优化策略不匹配。鉴于公平的基准，我们进行进一步的研究并发现网络结构的不对称性赋予对比框架在线性评估协议下正常工作，同时可能会损害长尾分类任务的转移性能。此外，负样本并不能使模型更明智地选择数据增强，也不会使不对称网络结构结构。我们相信我们的发现为将来的工作提供了有用的信息。

最近在自我监督学习中的最先进的框架最近表明，与传统的CNN型号相比，基于变压器的模型可以导致性能提升。繁荣以最大化图像的两个视图的相互信息，现有的作品对最终陈述具有对比损失。在我们的工作中，我们通过通过对比损失允许中间表示从最终层学习来进一步利用这一点，这可以最大化原始目标的上限和两层之间的相互信息。我们的方法，自蒸馏自我监督学习（SDSSL），胜过竞争基础（SIMCLR，BYOL和MOCO V3）使用各种任务和数据集。在线性评估和K-NN协议中，SDSSL不仅导致最终层的性能优异，而且在大多数下层中也是如此。此外，正负对准用于解释如何更有效地形成表示。代码将可用。

指数移动平均值（EMA或动量）被广泛用于现代自学学习（SSL）方法，例如MOCO，以提高性能。我们证明，这种动量也可以插入无动量的SSL框架（例如SIMCLR），以提高性能。尽管它广泛用作现代SSL框架中的基本组成部分，但动量造成的好处尚未得到充分理解。我们发现它的成功至少可以部分归因于稳定性效应。在第一次尝试中，我们分析了EMA如何影响编码器的每个部分，并揭示了编码器输入附近的部分起着微不足道的作用，而后者则具有更大的影响。通过监测编码器中每个块的输出的总体损失的梯度，我们观察到，最终层在反向传播过程中倾向于比其他层的波动大得多，即稳定性较小。有趣的是，我们表明，使用EMA到SSL编码器的最后一部分，即投影仪，而不是整个深层网络编码器可以提供可比或可比性的性能。我们提出的仅投影仪的动量有助于维持EMA的好处，但避免了双向计算。

最近，自我监督的蒙面自动编码器（MAE）因其令人印象深刻的表示能力而引起了前所未有的关注。但是，借口任务是掩盖的图像建模（MIM），重建缺失的本地贴片，缺乏对图像的全局理解。本文通过添加有监督的分类部门将MAE扩展到了完全监督的环境，从而使Mae可以从Golden Labels中有效地学习全球功能。所提出的监督MAE（Supmae）仅利用图像贴片的可见子集进行分类，这与使用所有图像贴片的标准监督预训练不同。通过实验，我们证明了Supmae不仅更有效地训练，而且还学会了更健壮和可转移的功能。具体而言，Supmae在使用VIT-B/16模型的ImageNet上评估时仅使用30％的计算来实现MAE的可比性。 Supmae对ImageNet变体的鲁棒性和转移学习绩效优于MAE和标准监督前培训对手。代码将公开可用。

本文提出了一种可扩展的方法，用于同时学习单个令牌和整体实例表示的分布式表示。我们使用自我注意解区块代表分布式令牌，然后是跨注意区块来汇总整体实例。该方法的核心是使用极大的令牌掩蔽（75％-90％）作为监督的数据增加。我们的模型命名为Oxtreara，遵循普通的BYOL方法，其中训练了来自未掩盖子集的实例表示从完整的输入中预测。学习需要模型在实例中捕获信息的变化，而不是鼓励不变。本文有三个贡献：1）随机掩盖是一种强大而有效的数据增强，用于学习可推广的注意力表示。 2）每个实例进行多次抽样，极端掩盖会大大加快学习的速度，并渴望获得更多数据。 3）与蒙版建模中的to徒监督不同，可以单独从实例监督中学到分布式表示形式。

由于具有强大的代表性，变形金刚在包括自然语言处理（NLP），计算机视觉和语音识别在内的广泛应用中越来越受欢迎。但是，利用这种代表性的能力有效地需要大量的数据，强大的正则化或两者兼而有之以减轻过度拟合。最近，基于掩盖的自动编码器的自我监督预处理策略已解锁了变压器的功能，这些策略依赖于直接或从未掩盖的内容对比的掩蔽输入进行重建。这种预训练的策略已在NLP中的BERT模型，Speak2VEC模型中使用，最近在Vision中的MAE模型中，该模型迫使该模型使用自动编码相关的目标来了解输入不同部分中的内容之间的关系。在本文中，我们提出了一种小说但令人惊讶的简单替代内容，以预测内容的位置，而无需为其提供位置信息。这样做需要变压器仅凭内容就可以理解输入不同部分之间的位置关系。这相当于有效的实现，其中借口任务是每个输入令牌所有可能位置之间的分类问题。我们在视觉和语音基准上进行了实验，我们的方法对强有力的监督训练基准进行了改进，并且与现代的无监督/自我监督预审方法相媲美。我们的方法还可以使经过训练的变压器在没有位置嵌入的情况下胜过训练有完整位置信息的训练的变压器。