Training data-efficient image transformers & distillation through attention

International Conference on Machine Learning (ICML)


Recently, neural networks purely based on attention were shown to address image understanding tasks such as image classification. These high-performing vision transformers are pre-trained with hundreds of millions of images using a large infrastructure, thereby limiting their adoption.

In this work, we produce competitive convolution-free transformers trained on ImageNet only using a single computer in less than 3 days. Our reference vision transformer (86M parameters) achieves top-1 accuracy of 83.1% (single-crop) on ImageNet with no external data.

We also introduce a teacher-student strategy specific to transformers. It relies on a distillation token ensuring that the student learns from the teacher through attention, typically from a convnet teacher. The learned transformers are competitive (85.2% top-1 acc.) with the state of the art on ImageNet, and similarly when transferred to other tasks. We will share our code and models.

Related Publications

All Publications

NeurIPS - December 6, 2021

Parallel Bayesian Optimization of Multiple Noisy Objectives with Expected Hypervolume Improvement

Samuel Daulton, Maximilian Balandat, Eytan Bakshy

arXiv - January 29, 2020

fastMRI: An Open Dataset and Benchmarks for Accelerated MRI

Jure Zbontar, Florian Knoll, Anuroop Sriram, Tullie Murrell, Zhengnan Huang, Matthew J. Muckley, Aaron Defazio, Ruben Stern, Patricia Johnson, Mary Bruno, Marc Parente, Krzysztof J. Geras, Joe Katsnelson, Hersh Chandarana, Zizhao Zhang, Michal Drozdzal, Adriana Romero, Michael Rabbat, Pascal Vincent, Nafissa Yakubova, James Pinkerton, Duo Wang, Erich Owens, Larry Zitnick, Michael P. Recht, Daniel K. Sodickson, Yvonne W. Lui

arXiv - April 20, 2021

MBRL-Lib: A Modular Library for Model-based Reinforcement Learning

Luis Pineda, Brandon Amos, Amy Zhang, Nathan O. Lambert, Roberto Calandra

ICCC - September 14, 2021

Visual Conceptual Blending with Large-scale Language and Vision Models

Songwei Ge, Devi Parikh

To help personalize content, tailor and measure ads, and provide a safer experience, we use cookies. By clicking or navigating the site, you agree to allow our collection of information on and off Facebook through cookies. Learn more, including about available controls: Cookie Policy