Recent neural compression methods have been based on the popular hyperprior framework. It relies on Scalar Quantization and offers a very strong compression performance. This contrasts from recent advances in image generation and representation learning, where Vector Quantization is more commonly employed. In this work, we attempt to bring these lines of research closer by revisiting vector quantization for image compression. We build upon the VQ-VAE framework and introduce several modifications. First, we replace the vanilla vector quantizer by a product quantizer. This intermediate solution between vector and scalar quantization allows for a much wider set of rate-distortion points: It implicitly defines high-quality quantizers that would otherwise require intractably large codebooks. Second, inspired by the success of Masked Image Modeling (MIM) in the context of self-supervised learning and generative image models, we propose a novel conditional entropy model which improves entropy coding by modelling the co-dependencies of the quantized latent codes. The resulting PQ-MIM model is surprisingly effective: its compression performance on par with recent hyperprior methods. It also outperforms HiFiC in terms of FID and KID metrics when optimized with perceptual losses (e.g. adversarial). Finally, since PQ-MIM is compatible with image generation frameworks, we show qualitatively that it can operate under a hybrid mode between compression and generation, with no further training or finetuning. As a result, we explore the extreme compression regime where an image is compressed into 200 bytes, i.e., less than a tweet.

基于变压器的体系结构已在各种视觉域（最著名的图像和视频）中变得更具竞争力。虽然先前的工作已经孤立地研究了这些模式，但拥有一个共同的体系结构表明，人们可以训练单个统一模型以多种视觉方式。事先尝试进行统一建模通常使用针对视觉任务量身定制的体系结构，或与单个模态模型相比获得较差的性能。在这项工作中，我们表明可以使用蒙版的自动编码来在图像和视频上训练简单的视觉变压器，而无需任何标记的数据。该单个模型学习了与图像和视频基准上的单模式表示相当或更好的视觉表示，同时使用了更简单的体系结构。特别是，我们的单一预算模型可以进行审核，以在ImageNet上获得86.5％的速度，而在挑战性的事物V2视频基准测试中，可以实现75.3％的范围。此外，可以通过丢弃90％的图像和95％的视频补丁来学习该模型，从而实现非常快速的训练。

我们展示了如何通过基于关注的全球地图扩充任何卷积网络，以实现非本地推理。我们通过基于关注的聚合层替换为单个变压器块的最终平均池，重量贴片如何参与分类决策。我们使用2个参数（宽度和深度）使用简单的补丁卷积网络，使用简单的补丁的卷积网络插入学习的聚合层。与金字塔设计相比，该架构系列在所有层上维护输入补丁分辨率。它在准确性和复杂性之间产生了令人惊讶的竞争权衡，特别是在记忆消耗方面，如我们在各种计算机视觉任务所示：对象分类，图像分割和检测的实验所示。

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。

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.