现实世界中的数据是高维的：即使在压缩后，书籍，图像或音乐表演也很容易包含数十万个元素。但是，最常用的自回归模型，变压器非常昂贵，以缩放捕获这种远程结构所需的输入和层数。我们开发了感知者AR，这是一种自回归的模态 - 不合骨架构，它使用交叉注意力将远程输入映射到少数潜在的潜在，同时还可以维护端到端的因果关系掩盖。感知器AR可以直接进行十万个令牌，从而实现了实用的长篇小写密度估计，而无需手工制作的稀疏模式或记忆机制。当对图像或音乐进行培训时，感知器AR会生成具有清晰长期连贯性和结构的输出。我们的架构还获得了长期基准测试的最新可能性，包括64 x 64个Imagenet图像和PG-19书籍。

Biological systems perceive the world by simultaneously processing high-dimensional inputs from modalities as diverse as vision, audition, touch, proprioception, etc. The perception models used in deep learning on the other hand are designed for individual modalities, often relying on domainspecific assumptions such as the local grid structures exploited by virtually all existing vision models. These priors introduce helpful inductive biases, but also lock models to individual modalities. In this paper we introduce the Perceiver -a model that builds upon Transformers and hence makes few architectural assumptions about the relationship between its inputs, but that also scales to hundreds of thousands of inputs, like ConvNets. The model leverages an asymmetric attention mechanism to iteratively distill inputs into a tight latent bottleneck, allowing it to scale to handle very large inputs. We show that this architecture is competitive with or outperforms strong, specialized models on classification tasks across various modalities: images, point clouds, audio, video, and video+audio. The Perceiver obtains performance comparable to ResNet-50 and ViT on ImageNet without 2D convolutions by directly attending to 50,000 pixels. It is also competitive in all modalities in AudioSet.

Self-attention has recently been adopted for a wide range of sequence modeling problems. Despite its effectiveness, self-attention suffers from quadratic compute and memory requirements with respect to sequence length. Successful approaches to reduce this complexity focused on attending to local sliding windows or a small set of locations independent of content. Our work proposes to learn dynamic sparse attention patterns that avoid allocating computation and memory to attend to content unrelated to the query of interest. This work builds upon two lines of research: it combines the modeling flexibility of prior work on content-based sparse attention with the efficiency gains from approaches based on local, temporal sparse attention. Our model, the Routing Transformer, endows selfattention with a sparse routing module based on online k-means while reducing the overall complexity of attention to O(n 1.5 d) from O(n 2 d) for sequence length n and hidden dimension d. We show that our model outperforms comparable sparse attention models on language modeling on Wikitext-103 (15.8 vs 18.3 perplexity), as well as on image generation on ImageNet-64 (3.43 vs 3.44 bits/dim) while using fewer self-attention layers. Additionally, we set a new state-of-the-art on the newly released PG-19 data-set, obtaining a test perplexity of 33.2 with a 22 layer Routing Transformer model trained on sequences of length 8192. We open-source the code for Routing Transformer in Tensorflow. *

状态空间模型已显示在建模远距离依赖性方面有效，特别是序列分类任务。在这项工作中，我们着重于对英语书籍，GitHub源代码和Arxiv数学文章的自回旋序列建模。基于围绕封闭激活功能的有效性的最新发展，我们提出了一个名为“封闭状态空间（GSS）”的新层，并表明它的训练速度明显快于TPU的S4（即DSS）的对角线版本，具有相当竞争力 - 基于变压器的基线，并表现出零击向更长的输入，同时直接实施。最后，我们表明，利用自我意见来建模局部依赖性，可以进一步提高GSS的性能。

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。

我们介绍了块状变压器，该变压器以序列的反复方式应用变压器层，并且相对于序列长度具有线性复杂性。我们的复发单元在训练过程中在代币的块而不是单个令牌上运行，并利用块内并行计算，以便有效利用加速器硬件。单元本身非常简单。它仅仅是一个变压器层：它使用自我注意事项和交叉注意力来有效计算大量状态向量和令牌上的复发函数。我们的设计部分受到LSTM单元的启发，它使用LSTM风格的大门，但它可以将典型的LSTM单元缩放为几个数量级。我们的复发实现在计算时间和参数计数中都具有相同的成本作为传统的变压器层，但是在很长的序列中，语言建模任务中的语言建模任务的困惑极大地改善了。我们的模型比远程变压器XL基线的表现宽大，同时运行的速度是两倍。我们证明了它在PG19（书籍），Arxiv论文和GitHub源代码上的有效性。我们的代码已发布为开​​源。

Transformers achieve remarkable performance in several tasks but due to their quadratic complexity, with respect to the input's length, they are prohibitively slow for very long sequences. To address this limitation, we express the self-attention as a linear dot-product of kernel feature maps and make use of the associativity property of matrix products to reduce the complexity from O N 2 to O (N ), where N is the sequence length. We show that this formulation permits an iterative implementation that dramatically accelerates autoregressive transformers and reveals their relationship to recurrent neural networks. Our linear transformers achieve similar performance to vanilla transformers and they are up to 4000x faster on autoregressive prediction of very long sequences.

Diffusion models have quickly become the go-to paradigm for generative modelling of perceptual signals (such as images and sound) through iterative refinement. Their success hinges on the fact that the underlying physical phenomena are continuous. For inherently discrete and categorical data such as language, various diffusion-inspired alternatives have been proposed. However, the continuous nature of diffusion models conveys many benefits, and in this work we endeavour to preserve it. We propose CDCD, a framework for modelling categorical data with diffusion models that are continuous both in time and input space. We demonstrate its efficacy on several language modelling tasks.

Large Transformer models routinely achieve state-of-the-art results on a number of tasks but training these models can be prohibitively costly, especially on long sequences. We introduce two techniques to improve the efficiency of Transformers. For one, we replace dot-product attention by one that uses locality-sensitive hashing, changing its complexity from O(L 2 ) to O(L log L), where L is the length of the sequence. Furthermore, we use reversible residual layers instead of the standard residuals, which allows storing activations only once in the training process instead of N times, where N is the number of layers. The resulting model, the Reformer, performs on par with Transformer models while being much more memory-efficient and much faster on long sequences.

基于变压器的模型在多个领域和任务上显示了它们的有效性。自我注意力允许将所有序列元素的信息结合到上下文感知表示形式中。但是，全球和本地信息必须主要存储在相同的元素表示中。此外，输入序列的长度受到自我注意的二次计算复杂性的限制。在这项工作中，我们提出并研究了一个记忆启动的片段级循环变压器（复发记忆变压器）。内存允许借助复发的帮助存储和处理本地和全局信息，并可以在长序列的段之间传递信息。我们通过将特殊的内存令牌添加到输入或输出序列中，实现了一个内存机制，无需更改变压器模型。然后，对变压器进行了训练，以控制内存操作和序列表示处理。实验的结果表明，我们的模型与Transformer-XL在语言建模上的较小内存大小上的表现相同，并在需要更长序列处理的任务方面胜过它。我们证明，将内存令牌添加到TR-XL可以提高IT性能。这使得反复的内存变压器成为需要学习长期依赖性和内存处理中的通用性（例如算法任务和推理）的应用程序的有前途的体系结构。

Astounding results from Transformer models on natural language tasks have intrigued the vision community to study their application to computer vision problems. Among their salient benefits, Transformers enable modeling long dependencies between input sequence elements and support parallel processing of sequence as compared to recurrent networks e.g., Long short-term memory (LSTM). Different from convolutional networks, Transformers require minimal inductive biases for their design and are naturally suited as set-functions. Furthermore, the straightforward design of Transformers allows processing multiple modalities (e.g., images, videos, text and speech) using similar processing blocks and demonstrates excellent scalability to very large capacity networks and huge datasets. These strengths have led to exciting progress on a number of vision tasks using Transformer networks. This survey aims to provide a comprehensive overview of the Transformer models in the computer vision discipline. We start with an introduction to fundamental concepts behind the success of Transformers i.e., self-attention, large-scale pre-training, and bidirectional feature encoding. We then cover extensive applications of transformers in vision including popular recognition tasks (e.g., image classification, object detection, action recognition, and segmentation), generative modeling, multi-modal tasks (e.g., visual-question answering, visual reasoning, and visual grounding), video processing (e.g., activity recognition, video forecasting), low-level vision (e.g., image super-resolution, image enhancement, and colorization) and 3D analysis (e.g., point cloud classification and segmentation). We compare the respective advantages and limitations of popular techniques both in terms of architectural design and their experimental value. Finally, we provide an analysis on open research directions and possible future works. We hope this effort will ignite further interest in the community to solve current challenges towards the application of transformer models in computer vision.

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.

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.

理想的音乐合成器应具有互动性和表现力，并实时产生高保真音频，以进行任意组合仪器和音符。最近的神经合成器在特定于域的模型之间表现出了折衷，这些模型仅对特定仪器或可以训练所有音乐训练但最小的控制和缓慢发电的原始波形模型提供了详细的控制。在这项工作中，我们专注于神经合成器的中间立场，这些基础可以从MIDI序列中产生音频，并实时使用仪器的任意组合。这使得具有单个模型的各种转录数据集的培训，这又提供了对各种仪器的组合和仪器的控制级别的控制。我们使用一个简单的两阶段过程：MIDI到具有编码器变压器的频谱图，然后使用生成对抗网络（GAN）频谱图逆变器将频谱图到音频。我们将训练解码器作为自回归模型进行了比较，并将其视为一种脱氧扩散概率模型（DDPM），并发现DDPM方法在定性上是优越的，并且通过音频重建和fr \'echet距离指标来衡量。鉴于这种方法的互动性和普遍性，我们发现这是迈向互动和表达性神经综合的有前途的第一步，以实现工具和音符的任意组合。

Transformers and variational autoencoders (VAE) have been extensively employed for symbolic (e.g., MIDI) domain music generation. While the former boast an impressive capability in modeling long sequences, the latter allow users to willingly exert control over different parts (e.g., bars) of the music to be generated. In this paper, we are interested in bringing the two together to construct a single model that exhibits both strengths. The task is split into two steps. First, we equip Transformer decoders with the ability to accept segment-level, time-varying conditions during sequence generation. Subsequently, we combine the developed and tested in-attention decoder with a Transformer encoder, and train the resulting MuseMorphose model with the VAE objective to achieve style transfer of long pop piano pieces, in which users can specify musical attributes including rhythmic intensity and polyphony (i.e., harmonic fullness) they desire, down to the bar level. Experiments show that MuseMorphose outperforms recurrent neural network (RNN) based baselines on numerous widely-used metrics for style transfer tasks.

我们通过与与前面令牌的局部相似度，通过调节从大语料库检索的文档块来增强自动回归语言模型。尽管使用25美元\时分，我们的检索增强型变压器（RetroCro）的检索增强型变压器（RetroCr）对GPT-3和侏罗纪-1获得了可比性的性能。微调后，复古表演转换为下游知识密集型任务，如问题应答。复古结合了冷冻BERT猎犬，一种可微分的编码器和块状的横向机制，以预测基于数量级的令牌，而不是训练期间通常消耗的数量。我们通常从头开始训练复古，还可以快速改造预先接受的变压器，通过检索，仍然达到良好的性能。我们的工作通过以前所未有的规模开辟了通过显式内存改进语言模型的新途径。

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.

上下文感知的str方法通常使用内部自回旋（AR）语言模型（LM）。 AR模型的固有局限性动机是采用外部LM的两阶段方法。输入图像上外部LM的条件独立性可能导致其错误地纠正正确的预测，从而导致明显的低效率。我们的方法Parseq使用置换语言建模学习了具有共同权重的内部AR LMS集合。它统一了无上下文的非AR和上下文感知的AR推断，并使用双向上下文统一了迭代的精致。使用合成训练数据，Parseq实现了最新的（SOTA），从而获得了Str基准（精度为91.9％）和更具挑战性的数据集。在对实际数据进行培训时，它建立了新的SOTA结果（精度为96.0％）。 Parseq由于其简单，统一的结构和平行的令牌处理，对准确性与参数计数，拖放和延迟非常最佳。由于其广泛使用了注意力，它对在现实世界图像中常见的任意导向文本具有鲁棒性。代码，预处理的权重和数据可在以下网址提供：https：//github.com/baudm/parseq。

在深度学习中，模型通常重用所有输入的相同参数。专家的混合（MOE）违反了这一点，而是为每个传入示例选择不同的参数。结果是一个稀疏激活的模型 - 具有残酷数量的参数 - 但恒定的计算成本。然而，尽管MOE取得了一些显着的成功，但复杂性，沟通成本和培训不稳定的阻碍了广泛的采用 - 我们使用Switch Transformer解决了这些领域。我们简化了MOE路由算法和设计直观的改进模型，以降低的通信和计算成本。我们提出的培训技术有助于纠缠不稳定，我们表明稀疏模型可能首次以较低的精度（BFLOAT16）格式进行培训。我们设计了基于T5基数和T5总数的模型，以使用相同的计算资源获得高达7倍的训练速度。这些改进扩展到多语言设置，我们在所有101种语言中衡量对MT5基本版本的收益。最后，我们通过在“巨大的清洁爬行语料库”上预先培训高达数万亿个参数模型，并在T5-XXL模型上实现4倍的速度，从而提高了语言模型的当前规模。

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