Lucas Beyer

17

Papers

254

Total Citations

Papers (17)

On Scaling Up a Multilingual Vision and Language Model

Revisiting Self-Supervised Visual Representation Learning

On Robustness and Transferability of Convolutional Neural Networks

LiT: Zero-Shot Transfer With Locked-Image Text Tuning

Knowledge Distillation: A Good Teacher Is Patient and Consistent

Kubric: A Scalable Dataset Generator

Scaling Vision Transformers

FlexiViT: One Model for All Patch Sizes

S4L: Self-Supervised Semi-Supervised Learning

Sigmoid Loss for Language Image Pre-Training

Big Transfer (BiT): General Visual Representation Learning

A Simple Single-Scale Vision Transformer for Object Detection and Instance Segmentation

MLP-Mixer: An all-MLP Architecture for Vision

UViM: A Unified Modeling Approach for Vision with Learned Guiding Codes

Getting ViT in Shape: Scaling Laws for Compute-Optimal Model Design

Three Towers: Flexible Contrastive Learning with Pretrained Image Models

Image Captioners Are Scalable Vision Learners Too