Vision Transformers (ViT) have been shown to attain highly competitive performance for a wide range of vision applications, such as image classification, object detection and semantic image segmentation. In comparison to convolutional neural networks, the Vision Transformer's weaker inductive bias is generally found to cause an increased reliance on model regularization or data augmentation ("AugReg" for short) when training on smaller training datasets. We conduct a systematic empirical study in order to better understand the interplay between the amount of training data, AugReg, model size and compute budget. As one result of this study we find that the combination of increased compute and AugReg can yield models with the same performance as models trained on an order of magnitude more training data: we train ViT models of various sizes on the public ImageNet-21k dataset which either match or outperform their counterparts trained on the larger, but not publicly available JFT-300M dataset.

A classical problem in computer vision is to infer a 3D scene representation from few images that can be used to render novel views at interactive rates. Previous work focuses on reconstructing pre-defined 3D representations, e.g. textured meshes, or implicit representations, e.g. radiance fields, and often requires input images with precise camera poses and long processing times for each novel scene. In this work, we propose the Scene Representation Transformer (SRT), a method which processes posed or unposed RGB images of a new area, infers a "set-latent scene representation", and synthesises novel views, all in a single feed-forward pass. To calculate the scene representation, we propose a generalization of the Vision Transformer to sets of images, enabling global information integration, and hence 3D reasoning. An efficient decoder transformer parameterizes the light field by attending into the scene representation to render novel views. Learning is supervised end-to-end by minimizing a novel-view reconstruction error. We show that this method outperforms recent baselines in terms of PSNR and speed on synthetic datasets, including a new dataset created for the paper. Further, we demonstrate that SRT scales to support interactive visualization and semantic segmentation of real-world outdoor environments using Street View imagery.

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.

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.

CUBBITT En-Fr translation models, exported via TensorFlow Serving, available in the Lindat translation service (https://lindat.mff.cuni.cz/services/translation/). Models are compatible with Tensor2tensor version 1.6.6. For details about the model training (data, model hyper-parameters), please contact the archive maintainer. Evaluation on newstest2014 (BLEU): en->fr: 38.2 fr->en: 36.7 (Evaluated using multeval: https://github.com/jhclark/multeval)

Neural Networks require large amounts of memory and compute to process high resolution images, even when only a small part of the image is actually informative for the task at hand. We propose a method based on a differentiable Top-K operator to select the most relevant parts of the input to efficiently process high resolution images. Our method may be interfaced with any downstream neural network, is able to aggregate information from different patches in a flexible way, and allows the whole model to be trained end-to-end using backpropagation. We show results for traffic sign recognition, inter-patch relationship reasoning, and fine-grained recognition without using object/part bounding box annotations during training.

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.

Learning object-centric representations of complex scenes is a promising step towards enabling efficient abstract reasoning from low-level perceptual features. Yet, most deep learning approaches learn distributed representations that do not capture the compositional properties of natural scenes. In this paper, we present the Slot Attention module, an architectural component that interfaces with perceptual representations such as the output of a convolutional neural network and produces a set of task-dependent abstract representations which we call slots. These slots are exchangeable and can bind to any object in the input by specializing through a competitive procedure over multiple rounds of attention. We empirically demonstrate that Slot Attention can extract object-centric representations that enable generalization to unseen compositions when trained on unsupervised object discovery and supervised property prediction tasks.

The invention relates to attention-based image generation neural networks. Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating an output image. In one aspect, one of the methods includes generating the output image intensity value by intensity value according to a generation order of pixel-color channel pairs from the output image, comprising, for each particular generation order position in the generation order: generating a current output image representation of a current output image, processing the current output image representation using a decoder neural network to generate a probability distribution over possible intensity values for the pixel-color channel pair at the particular generation order position, wherein the decoder neural network includes one or more local masked self-attention sub-layers; and selecting an intensity value for the pixel-color channel pair at the particular generation order position using theprobability distribution.

Methods, systems, and apparatus for generating data describing context clusters and context cluster probabilities, wherein each context cluster includes query inputs based on the input context for each of the query inputs and the content described by each query input, and each context cluster probability indicates a probability that at a query input that belongs to the context cluster will be selected by the user, receiving, from a user device, an indication of a user event that includes data indicating a context of the user device, selecting as a selected context cluster, based on the context cluster probabilities for each of the context clusters and the context of the user device, a context cluster for selection input by the user device, and providing, to the user device, data that causes the user device to display a context cluster selection input that indicates the selected context cluster for user selection.

metodos, sistemas e aparelho, incluindo programas de computador codificados em um meio de armazenamento em computador, para gerar uma sequencia de saidas a partir de uma sequencia de entradas. em um aspecto, um dos sistemas inclui uma rede neural codificadora configurada para receber a sequencia de entradas e gerar representacoes codificadas das entradas de rede, a rede neural codificadora compreendendo uma sequencia de uma ou mais sub-redes codificadoras, cada sub-rede codificadora configurada para receber uma respectiva entrada de sub-rede codificadora para cada uma das posicoes de entrada e para gerar uma respectiva saida de sub-rede para cada uma das posicoes de entrada, e cada sub-rede codificadora compreendendo: uma subcamada de autoatencao codificadora que e configurada para receber a entrada de sub-rede para cada uma das posicoes de entrada e, para cada posicao especifica de entrada na ordem de entrada: aplicar um mecanismo de atencao sobre as entradas de sub-redes codificadoras usando uma ou mais consultas obtidas a partir da entrada de sub-rede codificadora na posicao especifica de entrada.

The quality of human translation was long thought to be unattainable for computer translation systems. In this study, we present a deep-learning system, CUBBITT, which challenges this view. In a context-aware blind evaluation by human judges, CUBBITT significantly outperformed professional-agency English-to-Czech news translation in preserving text meaning (translation adequacy). While human translation is still rated as more fluent, CUBBITT is shown to be substantially more fluent than previous state-of-the-art systems. Moreover, most participants of a Translation Turing test struggle to distinguish CUBBITT translations from human translations. This work approaches the quality of human translation and even surpasses it in adequacy in certain circumstances.This suggests that deep learning may have the potential to replace humans in applications where conservation of meaning is the primary aim.

A method for generating a video is described. The method includes: generating an initial output video including multiple frames, each of the frames having multiple channels; identifying a partitioning of the initial output video into a set of channel slices that are indexed according to a particular slice order, each channel slice being a down sampling of a channel stack from a set of channel stacks; initializing, for each channel stack in the set of channel stacks, a set of fully-generated channel slices; repeatedly processing, using an encoder and a decoder, a current output video to generate a next fully-generated channel slice to be added to the current set of fully-generated channel slices; generating, for each channel index, a respective fully-generated channel stack using the respective fully generated channel slices; and generating a fully-generated output video using the fully-generated channel stacks.

Due to the statistical complexity of video, the high degree of inherent stochasticity, and the sheer amount of data, generating natural video remains a challenging task. State-of-the-art video generation models often attempt to address these issues by combining sometimes complex, usually video-specific neural network architectures, latent variable models, adversarial training and a range of other methods. Despite their often high complexity, these approaches still fall short of generating high quality video continuations outside of narrow domains and often struggle with fidelity. In contrast, we show that conceptually simple autoregressive video generation models based on a three-dimensional self-attention mechanism achieve competitive results across multiple metrics on popular benchmark datasets, for which they produce continuations of high fidelity and realism. We also present results from training our models on Kinetics, a large scale action recognition dataset comprised of YouTube videos exhibiting phenomena such as camera movement, complex object interactions and diverse human movement. While modeling these phenomena consistently remains elusive, we hope that our results, which include occasional realistic continuations encourage further research on comparatively complex, large scale datasets such as Kinetics.

Communication between slots In Slot Attention, slots only communicate via the softmax attention over the input keys, which is normalized across slots. This choice of normalization establishes competition between the slots for explaining parts of the input, which can drive specialization of slots to objects. In some scenarios it can make sense to introduce a more explicit form of communication between slots, e.g. via slot-to-slot message passing in the form of a graph neural network as in [3, 4] or self-attention [5–9]. This can be beneficial for modeling systems of objects that interact dynamically [3, 4, 8] or for set generation conditioned on a single vector (as opposed to an image or a set of vectors) [9].

In this paper, we offer a preliminary investigation into the task of in-image machine translation: transforming an image containing text in one language into an image containing the same text in another language. We propose an end-to-end neural model for this task inspired by recent approaches to neural machine translation, and demonstrate promising initial results based purely on pixel-level supervision. We then offer a quantitative and qualitative evaluation of our system outputs and discuss some common failure modes. Finally, we conclude with directions for future work.

We present the Natural Questions corpus, a question answering data set. Questions consist of real anonymized, aggregated queries issued to the Google search engine. An annotator is presented with a question along with a Wikipedia page from the top 5 search results, and annotates a long answer (typically a paragraph) and a short answer (one or more entities) if present on the page, or marks null if no long/short answer is present. The public release consists of 307,373 training examples with single annotations; 7,830 examples with 5-way annotations for development data; and a further 7,842 examples with 5-way annotated sequestered as test data. We present experiments validating quality of the data. We also describe analysis of 25-way annotations on 302 examples, giving insights into human variability on the annotation task. We introduce robust metrics for the purposes of evaluating question answering systems; demonstrate high human upper bounds on these metrics; and establish baseline results using competitive methods drawn from related literature.

Music relies heavily on repetition to build structure and meaning. Self-reference occurs on multiple timescales, from motifs to phrases to reusing of entire sections of music, such as in pieces with ABA structure. The Transformer (Vaswani et al., 2017), a sequence model based on self-attention, has achieved compelling results in many generation tasks that require maintaining long-range coherence. This suggests that self-attention might also be well-suited to modeling music. In musical composition and performance, however, relative timing is critically important. Existing approaches for representing relative positional information in the Transformer modulate attention based on pairwise distance (Shaw et al., 2018). This is impractical for long sequences such as musical compositions since their memory complexity is quadratic in the sequence length. We propose an algorithm that reduces the intermediate memory requirements to linear in the sequence length. This enables us to demonstrate that a Transformer with our modified relative attention mechanism can generate minute-long (thousands of steps) compositions with compelling structure, generate continuations that coherently elaborate on a given motif, and in a seq2seq setup generate accompaniments conditioned on melodies. We evaluate the Transformer with our relative attention mechanism on two datasets, JSB Chorales and Piano-e-competition, and obtain state-of-the-art results on the latter.

Recurrent neural networks (RNNs) sequentially process data by updating their state with each new data point, and have long been the de facto choice for sequence modeling tasks. However, their inherently sequential computation makes them slow to train. Feed-forward and convolutional architectures have recently been shown to achieve superior results on some sequence modeling tasks such as machine translation, with the added advantage that they concurrently process all inputs in the sequence, leading to easy parallelization and faster training times. Despite these successes, however, popular feed-forward sequence models like the Transformer fail to generalize in many simple tasks that recurrent models handle with ease, e.g. copying strings or even simple logical inference when the string or formula lengths exceed those observed at training time. We propose the Universal Transformer (UT), a parallel-in-time self-attentive recurrent sequence model which can be cast as a generalization of the Transformer model and which addresses these issues. UTs combine the parallelizability and global receptive field of feed-forward sequence models like the Transformer with the recurrent inductive bias of RNNs. We also add a dynamic per-position halting mechanism and find that it improves accuracy on several tasks. In contrast to the standard Transformer, under certain assumptions, UTs can be shown to be Turing-complete. Our experiments show that UTs outperform standard Transformers on a wide range of algorithmic and language understanding tasks, including the challenging LAMBADA language modeling task where UTs achieve a new state of the art, and machine translation where UTs achieve a 0.9 BLEU improvement over Transformers on the WMT14 En-De dataset.