Lucas Beyer

Lucas Beyer

Authored Publications
Sort By
  • Title
  • Title, descending
  • Year
  • Year, descending
    Preview abstract We explore the boundaries of scaling up a multilingual vision and language model, both in terms of size of the components and the breadth of its training task mixture. Our model achieves new levels of performance on a wide-range of varied and complex tasks, including multiple image-based captioning and question-answering tasks, image-based document understanding and few-shot (in-context) learning, as well as object detection, video question answering, and video captioning. Our model advances the state-of-the-art on most vision-and-language benchmarks considered (20+ of them). Finally, we observe emerging capabilities, such as complex counting and multilingual object detection, tasks that are not explicitly in the training mix. View details
    Preview abstract Effective scaling and a flexible task interface enable large-capacity language models to excel at many tasks. PaLI (Pathways Language and Image model) extends these ideas to the joint modeling of language and vision. PaLI is a model that generates text based on visual and textual inputs. Using this API, PaLI is able to perform many vision, language, and multimodal tasks, across many languages. We train PaLI with two main principles: reuse of pretrained unimodal components, and joint scaling of modalities. Using large-capacity pretrained language models and vision models allows us to capitalize on their existing capabilities, while leveraging the substantial cost of training them. We scale PaLI models across three axes:the language component, the vision component, and the training data that fuses them. For the vision component, we train the largest and best-performing VisionTransformer (ViT) to date. For the data, we build an image-text training set over10B images and covering over 100 languages. PaLI inherits and enhances language-understanding capabilities, and achieves state-of-the-art in multiple vision and language tasks (image classification, image captioning, visual question-answering, scene-text understanding, etc.), based on a simple, modular, and reuse-friendly platform for modeling and scaling. View details
    Preview abstract The scaling of Transformers has driven breakthrough capabilities for language models. At present, the largest large language models (LLMs) contain upwards of 100B parameters. Vision Transformers (ViT) have introduced the same architecture to image and video modeling, but these have not yet been successfully scaled to nearly the same degree; the largest dense ViT contains 4B parameters. We present a recipe for highly efficient training of a 22B-parameter ViT and perform a wide variety of experiments on the resulting model. When evaluated on downstream tasks (often with a lightweight linear model on frozen features) ViT22B demonstrates increasing performance with scale. We further observe other interesting benefits of scale, including an improved tradeoff between bias and performance, an improved alignment to human visual perception in terms of shape/texture bias, and improved robustness. ViT22B demonstrates the potential for "LLM-like'' scaling in vision, and provides key steps towards getting there. View details
    Preview abstract Attention-based neural networks such as the Vision Transformer (ViT) have recently attained state-of-the-art results on many computer vision benchmarks. Scale is a primary ingredient in attaining excellent results, therefore, understanding a model's scaling properties is a key to designing future generations effectively. While the laws for scaling Transformer language models have been studied, it is unknown how Vision Transformers scale. To address this, we scale ViT models and data, both up and down, and characterize the relationships between error rate, data, and compute. Along the way, we refine the architecture and training of ViT, reducing memory consumption and increasing accuracy of the resulting models. As a result, we successfully train a ViT model with two billion parameters, which attains a new state-of-the-art on ImageNet of 90.45% top-1 accuracy. The model also performs well for few-shot transfer, for example, reaching 84.86% top-1 accuracy on ImageNet with only 10 examples per class. View details
    Preview abstract It is commonly accepted that the Vision Transformer model requires sophisticated regularization techniques to excel at ImageNet-1k scale data. Surprisingly, we find this is not the case and standard data augmentation is sufficient. This note presents a few minor modifications to the original Vision Transformer (ViT) vanilla training setting that dramatically improve the performance of plain ViT models. Notably, 90 epochs of training surpass 76% top-1 accuracy in under seven hours on a TPUv3-8, similar to the classic ResNet50 baseline, and 300 epochs of training reach 80% in less than one day. View details
    Preview abstract There is a growing discrepancy in computer vision between large-scale models that achieve state-of-the-art performance and models that are affordable in practical applications. In this paper we address this issue and significantly bridge the gap between these two types of models. Throughout our empirical investigation we do not aim to necessarily propose a new method, but strive to identify a robust and effective recipe for making state-of-the-art large scale models affordable in practice. We demonstrate that, when performed correctly, knowledge distillation can be a powerful tool for reducing the size of large models without compromising their performance. In particular, we uncover that there are certain implicit design choices, which may drastically affect the effectiveness of distillation. Our key contribution is the explicit identification of these design choices, which were not previously articulated in the literature. We back up our findings by a comprehensive empirical study, demonstrate compelling results on a wide range of vision datasets and, in particular, obtain a state-of-the-art ResNet-50 model for ImageNet, which achieves 82.8% top-1 accuracy. View details
    Kubric: A scalable dataset generator
    Anissa Yuenming Mak
    Austin Stone
    Carl Doersch
    Cengiz Oztireli
    Charles Herrmann
    Daniel Rebain
    Derek Nowrouzezahrai
    Dmitry Lagun
    Fangcheng Zhong
    Florian Golemo
    Francois Belletti
    Henning Meyer
    Hsueh-Ti (Derek) Liu
    Issam Laradji
    Klaus Greff
    Kwang Moo Yi
    Matan Sela
    Noha Radwan
    Thomas Kipf
    Tianhao Wu
    Vincent Sitzmann
    Yilun Du
    Yishu Miao
    (2022)
    Preview abstract Data is the driving force of machine learning. The amount and quality of training data is often more important for the performance of a system than the details of its architecture. Data is also an important tool for testing specific hypothesis, and for empirically evaluating the behaviour of complex systems. Synthetic data generation represents a powerful tool that can address all these shortcomings: 1) it is cheap 2) supports rich ground-truth annotations 3) offers full control over data and 4) can circumvent privacy and legal concerns. Unfortunately the toolchain for generating data is less well developed than that for building models. We aim to improve this situation by introducing Kubric: a scalable open-source pipeline for generating realistic image and video data with rich ground truth annotations. We also publish a collection of generated datasets and baseline results on several vision tasks. View details
    Preview abstract While the Transformer architecture has become the de-facto standard for natural language processing tasks, its applications to computer vision remain limited. In vision tasks, attention is usually 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 ConvNets is not necessary and a pure transformer can perform very well on image classification tasks when applied directly to sequences of image patches. When pre-trained on large amounts of data and transferred to multiple recognition benchmarks (ImageNet, CIFAR-10, etc), these transformers attain excellent accuracy, matching or outperforming the best convolutional networks while requiring substantially less computational resources to train. View details
    On Robustness and Transferability of Convolutional Neural Networks
    Josip Djolonga
    Jessica Yung
    Michael Tschannen
    Rob Romijnders
    Dan Moldovan
    Sylvain Gelly
    Conference on Computer Vision and Pattern Recognition(2021)
    Preview abstract Modern deep convolutional networks (CNNs) are often criticized for their failure to generalize under distributional shifts. However, several recent breakthroughs in transfer learning suggest that these networks can cope with severe distribution shifts and successfully adapt to new tasks from a few training examples. In this work we revisit the out-of-distribution and transfer performance of modern image classification CNNs and investigate the impact of the pre-training data scale, the model scale, and the data preprocessing pipeline. We find that increasing both the training set and model sizes significantly improve the robustness to distribution shifts. Furthermore, we show that, perhaps surprisingly, simple changes in the preprocessing such as modifying the image resolution can significantly mitigate robustness issues in some cases. Finally, we outline the shortcomings of existing robustness evaluation datasets and introduce a synthetic dataset for fine-grained robustness analysis. View details
    Preview abstract 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 comparable pre-training and inference cost. We hope that these results spark further research beyond the realms of well established CNNs and Transformers. View details