Papers
arxiv:2403.13298

Rotary Position Embedding for Vision Transformer

Published on Mar 20
Authors:
,
,

Abstract

Rotary Position Embedding (RoPE) performs remarkably on language models, especially for length extrapolation of Transformers. However, the impacts of RoPE on computer vision domains have been underexplored, even though RoPE appears capable of enhancing Vision Transformer (ViT) performance in a way similar to the language domain. This study provides a comprehensive analysis of RoPE when applied to ViTs, utilizing practical implementations of RoPE for 2D vision data. The analysis reveals that RoPE demonstrates impressive extrapolation performance, i.e., maintaining precision while increasing image resolution at inference. It eventually leads to performance improvement for ImageNet-1k, COCO detection, and ADE-20k segmentation. We believe this study provides thorough guidelines to apply RoPE into ViT, promising improved backbone performance with minimal extra computational overhead. Our code and pre-trained models are available at https://github.com/naver-ai/rope-vit

Community

Sign up or log in to comment

Models citing this paper 21

Browse 21 models citing this paper

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2403.13298 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2403.13298 in a Space README.md to link it from this page.

Collections including this paper 1