COMPUTER VISION

Early Convolutions Help Transformers See Better

December 06, 2021

Abstract

Vision transformer (ViT) models exhibit substandard optimizability. In particular, they are sensitive to the choice of optimizer (AdamW vs. SGD), optimizer hyperparameters, and training schedule length. In comparison, modern convolutional neural networks are easier to optimize. Why is this the case? In this work, we conjecture that the issue lies with the patchify stem of ViT models, which is implemented by a stride-p p×p convolution (p = 16 by default) applied to the input image. This large-kernel plus large-stride convolution runs counter to typical design choices of convolutional layers in neural networks. To test whether this atypical design choice causes an issue, we analyze the optimization behavior of ViT models with their original patchify stem versus a simple counterpart where we replace the ViT stem by a small number of stacked stride-two 3×3 convolutions. While the vast majority of computation in the two ViT designs is identical, we find that this small change in early visual processing results in markedly different training behavior in terms of the sensitivity to optimization settings as well as the final model accuracy. Using a convolutional stem in ViT dramatically increases optimization stability and also improves peak performance (by ∼1-2% top-1 accuracy on ImageNet-1k), while maintaining flops and runtime. The improvement can be observed across the wide spectrum of model complexities (from 1G to 36G flops) and dataset scales (from ImageNet-1k to ImageNet-21k). These findings lead us to recommend using a standard, lightweight convolutional stem for ViT models in this regime as a more robust architectural choice compared to the original ViT model design.

Download the Paper

AUTHORS

Written by

Tete Xiao

Mannat Singh

Eric Mintun

Trevor Darrell

Piotr Dollar

Ross Girshick

Publisher

NeurIPS

Research Topics

Computer Vision

Related Publications

July 23, 2024

COMPUTER VISION

Imagine yourself: Tuning-Free Personalized Image Generation

Zecheng He, Bo Sun, Felix Xu, Haoyu Ma, Ankit Ramchandani, Vincent Cheung, Siddharth Shah, Anmol Kalia, Ning Zhang, Peizhao Zhang, Roshan Sumbaly, Peter Vajda, Animesh Sinha

July 23, 2024

July 23, 2024

HUMAN & MACHINE INTELLIGENCE

CONVERSATIONAL AI

The Llama 3 Herd of Models

Llama team

July 23, 2024

July 02, 2024

GRAPHICS

COMPUTER VISION

Meta 3D AssetGen: Text-to-Mesh Generation with High-Quality Geometry, Texture, and PBR Materials

Yawar Siddiqui, Tom Monnier, Filippos Kokkinos, Mahendra Kariya, Yanir Kleiman, Emilien Garreau, Oran Gafni, Natalia Neverova, Andrea Vedaldi, Roman Shapovalov, David Novotny

July 02, 2024

July 02, 2024

GRAPHICS

COMPUTER VISION

Meta 3D Gen

Raphael Bensadoun, Tom Monnier, Yanir Kleiman, Filippos Kokkinos, Yawar Siddiqui, Mahendra Kariya, Omri Harosh, Roman Shapovalov, Emilien Garreau, Animesh Karnewar, Ang Cao, Idan Azuri, Iurii Makarov, Eric-Tuan Le, Antoine Toisoul, David Novotny, Oran Gafni, Natalia Neverova, Andrea Vedaldi

July 02, 2024

Help Us Pioneer The Future of AI

We share our open source frameworks, tools, libraries, and models for everything from research exploration to large-scale production deployment.