Inspired by progress in unsupervised representation learning for natural language, we examine whether similar models can learn useful representations for images. We train a sequence Transformer to auto-regressively predict pixels, without incorporating knowledge of the 2D input structure. Despite training on low-resolution ImageNet without labels, we find that a GPT-2 scale model learns strong image representations as measured by linear probing, fine-tuning, and low-data classification. On CIFAR-10, we achieve 96.3% accuracy with a linear probe, outperforming a supervised Wide ResNet, and 99.0% accuracy with full fine-tuning, matching the top supervised pretrained models. We are also competitive with self-supervised benchmarks on ImageNet when substituting pixels for a VQVAE encoding, achieving 69.0% top-1 accuracy on a linear probe of our features.

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

我们引入了一个自我监督的视觉表示模型BEIT，该模型代表来自图像变压器的双向编码器表示。在Bert在自然语言处理区域中开发后，我们提出了一项掩盖的图像建模任务，以预识视觉变压器。具体而言，每个图像在我们的预训练中具有两个视图，即图像贴片（例如16x16像素）和视觉令牌（即离散令牌）。我们首先将原始图像“将”“令牌化”到视觉令牌中。然后，我们随机掩盖了一些图像补丁并将其喂入骨干变压器中。预训练的目标是根据损坏的图像补丁恢复原始的视觉令牌。在预训练BEIT之后，我们通过将任务层附加在预审计的编码器上，直接通过将任务层附加到下游任务上的模型参数。图像分类和语义分割的实验结果表明，我们的模型通过以前的预训练方法实现了竞争结果。例如，基本大小的BEIT在Imagenet-1K上获得了83.2％的TOP-1精度，并以相同的设置优于划痕DEIT训练（81.8％）。此外，大尺寸的BEIT仅使用Imagenet-1K获得86.3％，即使在Imagenet-22K上进行预训练（85.2％），甚至超过了VIT-L。代码和预估计的模型可在https://aka.ms/beit上找到。

Autoregressive language modeling (ALM) have been successfully used in self-supervised pre-training in Natural language processing (NLP). However, this paradigm has not achieved comparable results with other self-supervised approach in computer vision (e.g., contrastive learning, mask image modeling). In this paper, we try to find the reason why autoregressive modeling does not work well on vision tasks. To tackle this problem, we fully analyze the limitation of visual autoregressive methods and proposed a novel stochastic autoregressive image modeling (named SAIM) by the two simple designs. First, we employ stochastic permutation strategy to generate effective and robust image context which is critical for vision tasks. Second, we create a parallel encoder-decoder training process in which the encoder serves a similar role to the standard vision transformer focus on learning the whole contextual information, and meanwhile the decoder predicts the content of the current position, so that the encoder and decoder can reinforce each other. By introducing stochastic prediction and the parallel encoder-decoder, SAIM significantly improve the performance of autoregressive image modeling. Our method achieves the best accuracy (83.9%) on the vanilla ViT-Base model among methods using only ImageNet-1K data. Transfer performance in downstream tasks also show that our model achieves competitive performance.

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。

This paper presents SimCLR: a simple framework for contrastive learning of visual representations. We simplify recently proposed contrastive selfsupervised learning algorithms without requiring specialized architectures or a memory bank. In order to understand what enables the contrastive prediction tasks to learn useful representations, we systematically study the major components of our framework. We show that (1) composition of data augmentations plays a critical role in defining effective predictive tasks, (2) introducing a learnable nonlinear transformation between the representation and the contrastive loss substantially improves the quality of the learned representations, and (3) contrastive learning benefits from larger batch sizes and more training steps compared to supervised learning. By combining these findings, we are able to considerably outperform previous methods for self-supervised and semi-supervised learning on ImageNet. A linear classifier trained on self-supervised representations learned by Sim-CLR achieves 76.5% top-1 accuracy, which is a 7% relative improvement over previous state-ofthe-art, matching the performance of a supervised ResNet-50. When fine-tuned on only 1% of the labels, we achieve 85.8% top-5 accuracy, outperforming AlexNet with 100× fewer labels. 1

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。

Human observers can learn to recognize new categories of images from a handful of examples, yet doing so with artificial ones remains an open challenge. We hypothesize that data-efficient recognition is enabled by representations which make the variability in natural signals more predictable. We therefore revisit and improve Contrastive Predictive Coding, an unsupervised objective for learning such representations. This new implementation produces features which support state-of-theart linear classification accuracy on the ImageNet dataset. When used as input for non-linear classification with deep neural networks, this representation allows us to use 2-5× less labels than classifiers trained directly on image pixels. Finally, this unsupervised representation substantially improves transfer learning to object detection on the PASCAL VOC dataset, surpassing fully supervised pre-trained ImageNet classifiers.

大规模数据集的预培训模型，如想象成，是计算机视觉中的标准实践。此范例对于具有小型培训套的任务特别有效，其中高容量模型往往会过度装备。在这项工作中，我们考虑一个自我监督的预训练场景，只能利用目标任务数据。我们考虑数据集，如斯坦福汽车，草图或可可，这是比想象成小的数量的顺序。我们的研究表明，在本文中介绍的Beit或诸如Beit或Variant的去噪对预训练数据的类型和大小比通过比较图像嵌入来训练的流行自我监督方法更加强大。我们获得了竞争性能与ImageNet预训练相比，来自不同域的各种分类数据集。在Coco上，当专注于使用Coco Images进行预训练时，检测和实例分割性能超过了可比设置中的监督Imagenet预训练。

This work tackles the problem of semi-supervised learning of image classifiers. Our main insight is that the field of semi-supervised learning can benefit from the quickly advancing field of self-supervised visual representation learning. Unifying these two approaches, we propose the framework of self-supervised semi-supervised learning (S 4 L) and use it to derive two novel semi-supervised image classification methods. We demonstrate the effectiveness of these methods in comparison to both carefully tuned baselines, and existing semi-supervised learning methods. We then show that S 4 L and existing semi-supervised methods can be jointly trained, yielding a new state-of-the-art result on semi-supervised ILSVRC-2012 with 10% of labels.

变形金刚和蒙版语言建模在计算机视觉中很快被视为视觉变压器和蒙版图像建模（MIM）。在这项工作中，我们认为由于图像中令牌的数量和相关性，图像令牌掩盖与文本中的令牌掩盖有所不同。特别是，为了为MIM产生具有挑战性的借口任务，我们主张从随机掩盖到知情掩盖的转变。我们在基于蒸馏的MIM的背景下开发并展示了这一想法，其中教师变压器编码器生成了一个注意力图，我们用它来指导学生为学生指导掩盖。因此，我们引入了一种新颖的掩蔽策略，称为注意引导蒙版（ATTMASK），我们证明了其对基于密集蒸馏的MIM以及基于普通蒸馏的自然剥离的自助力学习的有效性。我们确认ATTMASK可以加快学习过程，并提高各种下游任务的性能。我们在https://github.com/gkakogeorgiou/attmask上提供实现代码。

Convolutional Neural Networks (CNNs) are the go-to model for computer vision. Recently, attention-based networks, such as the Vision Transformer, have also become popular. In this paper we show that while convolutions and attention are both sufficient for good performance, neither of them are necessary. We present MLP-Mixer, an architecture based exclusively on multi-layer perceptrons (MLPs). MLP-Mixer contains two types of layers: one with MLPs applied independently to image patches (i.e. "mixing" the per-location features), and one with MLPs applied across patches (i.e. "mixing" spatial information). When trained on large datasets, or with modern regularization schemes, MLP-Mixer attains competitive scores on image classification benchmarks, with pre-training and inference cost comparable to state-of-the-art models. We hope that these results spark further research beyond the realms of well established CNNs and Transformers. 1

State-of-the-art computer vision systems are trained to predict a fixed set of predetermined object categories. This restricted form of supervision limits their generality and usability since additional labeled data is needed to specify any other visual concept. Learning directly from raw text about images is a promising alternative which leverages a much broader source of supervision. We demonstrate that the simple pre-training task of predicting which caption goes with which image is an efficient and scalable way to learn SOTA image representations from scratch on a dataset of 400 million (image, text) pairs collected from the internet. After pre-training, natural language is used to reference learned visual concepts (or describe new ones) enabling zero-shot transfer of the model to downstream tasks. We study the performance of this approach by benchmarking on over 30 different existing computer vision datasets, spanning tasks such as OCR, action recognition in videos, geo-localization, and many types of fine-grained object classification. The model transfers non-trivially to most tasks and is often competitive with a fully supervised baseline without the need for any dataset specific training. For instance, we match the accuracy of the original ResNet-50 on ImageNet zero-shot without needing to use any of the 1.28 million training examples it was trained on. We release our code and pre-trained model weights at https://github.com/OpenAI/CLIP.

生成建模研究的持续趋势是将样本分辨率推高更高，同时减少培训和采样的计算要求。我们的目标是通过技术的组合进一步推动这一趋势 - 每个组件代表当前效率在各自领域的顶峰。其中包括载体定量的GAN（VQ-GAN），该模型具有高水平的损耗 - 但感知上微不足道的压缩模型；沙漏变形金刚，一个高度可扩展的自我注意力模型；和逐步未胶片的denoising自动编码器（Sundae），一种非自动化（NAR）文本生成模型。出乎意料的是，当应用于多维数据时，我们的方法突出了沙漏变压器的原始公式中的弱点。鉴于此，我们建议对重采样机制进行修改，该机制适用于将分层变压器应用于多维数据的任何任务。此外，我们证明了圣代表到长序列长度的可伸缩性 - 比先前的工作长四倍。我们提出的框架秤达到高分辨率（$ 1024 \ times 1024 $），并迅速火车（2-4天）。至关重要的是，训练有素的模型在消费级GPU（GTX 1080TI）上大约2秒内生产多样化和现实的百像样品。通常，该框架是灵活的：支持任意数量的采样步骤，示例自动插入，自我纠正功能，有条件的生成和NAR公式，以允许任意介绍掩护。我们在FFHQ256上获得10.56的FID得分 - 仅在100个采样步骤中以不到一半的采样步骤接近原始VQ -GAN，而FFHQ1024的FFHQ1024和21.85。

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。

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.

Designed to learn long-range interactions on sequential data, transformers continue to show state-of-the-art results on a wide variety of tasks. In contrast to CNNs, they contain no inductive bias that prioritizes local interactions. This makes them expressive, but also computationally infeasible for long sequences, such as high-resolution images. We demonstrate how combining the effectiveness of the inductive bias of CNNs with the expressivity of transformers enables them to model and thereby synthesize high-resolution images. We show how to (i) use CNNs to learn a contextrich vocabulary of image constituents, and in turn (ii) utilize transformers to efficiently model their composition within high-resolution images. Our approach is readily applied to conditional synthesis tasks, where both non-spatial information, such as object classes, and spatial information, such as segmentations, can control the generated image. In particular, we present the first results on semanticallyguided synthesis of megapixel images with transformers and obtain the state of the art among autoregressive models on class-conditional ImageNet. Code and pretrained models can be found at https://git.io/JnyvK.

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。

Transfer learning, where a model is first pre-trained on a data-rich task before being finetuned on a downstream task, has emerged as a powerful technique in natural language processing (NLP). The effectiveness of transfer learning has given rise to a diversity of approaches, methodology, and practice. In this paper, we explore the landscape of transfer learning techniques for NLP by introducing a unified framework that converts all text-based language problems into a text-to-text format. Our systematic study compares pre-training objectives, architectures, unlabeled data sets, transfer approaches, and other factors on dozens of language understanding tasks. By combining the insights from our exploration with scale and our new "Colossal Clean Crawled Corpus", we achieve state-of-the-art results on many benchmarks covering summarization, question answering, text classification, and more. To facilitate future work on transfer learning for NLP, we release our data set, pre-trained models, and code.

General perception systems such as Perceivers can process arbitrary modalities in any combination and are able to handle up to a few hundred thousand inputs. They achieve this generality by using exclusively global attention operations. This however hinders them from scaling up to the inputs sizes required to process raw high-resolution images or video. In this paper, we show that some degree of locality can be introduced back into these models, greatly improving their efficiency while preserving their generality. To scale them further, we introduce a self-supervised approach that enables learning dense low-dimensional positional embeddings for very large signals. We call the resulting model a Hierarchical Perceiver (HiP). In sum our contributions are: 1) scaling Perceiver-type models to raw high-resolution images and audio+video, 2) showing the feasibility of learning 1M+ positional embeddings from scratch using masked auto-encoding, 3) demonstrating competitive performance on raw data from ImageNet, AudioSet, PASCAL VOC, ModelNet40 and Kinetics datasets with the same exact, unchanged model and without specialized preprocessing or any tokenization.