Papers
arxiv:2202.12015

Learning to Merge Tokens in Vision Transformers

Published on Feb 24, 2022
Authors:
,
,
,
,
,

Abstract

Transformers are widely applied to solve natural language understanding and computer vision tasks. While scaling up these architectures leads to improved performance, it often comes at the expense of much higher computational costs. In order for large-scale models to remain practical in real-world systems, there is a need for reducing their computational overhead. In this work, we present the PatchMerger, a simple module that reduces the number of patches or tokens the network has to process by merging them between two consecutive intermediate layers. We show that the PatchMerger achieves a significant speedup across various model sizes while matching the original performance both upstream and downstream after fine-tuning.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2202.12015 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2202.12015 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/2202.12015 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.