Towards Efficient Vision State Space Models via Token Merging

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Park, Jinyoung, Son, Minseok, Kim, Changick
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915451234156544
author Park, Jinyoung
Son, Minseok
Kim, Changick
author_facet Park, Jinyoung
Son, Minseok
Kim, Changick
contents State Space Models (SSMs) have emerged as powerful architectures in computer vision, yet improving their computational efficiency remains crucial for practical and scalable deployment.While token reduction serves as an effective approach for model efficiency, applying it to SSMs requires careful consideration of their unique sequential modeling capabilities.In this work, we propose MaMe, a token-merging strategy tailored for SSM-based vision models.MaMe addresses two key challenges: quantifying token importance and preserving sequential properties. Our approach leverages the state transition parameter $\mathbfΔ$ as an informativeness measure and introduces strategic token arrangements to preserve sequential information flow.Extensive experiments demonstrate that MaMe achieves superior efficiency-performance trade-offs for both fine-tuned and off-the-shelf models. Particularly, our approach maintains robustness even under aggressive token reduction where existing methods undergo significant performance degradation.Beyond image classification, MaMe shows strong generalization capabilities across video and audio domains, establishing an effective approach for enhancing efficiency in diverse SSM applications.
format Preprint
id arxiv_https___arxiv_org_abs_2508_13599
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Towards Efficient Vision State Space Models via Token Merging
Park, Jinyoung
Son, Minseok
Kim, Changick
Computer Vision and Pattern Recognition
State Space Models (SSMs) have emerged as powerful architectures in computer vision, yet improving their computational efficiency remains crucial for practical and scalable deployment.While token reduction serves as an effective approach for model efficiency, applying it to SSMs requires careful consideration of their unique sequential modeling capabilities.In this work, we propose MaMe, a token-merging strategy tailored for SSM-based vision models.MaMe addresses two key challenges: quantifying token importance and preserving sequential properties. Our approach leverages the state transition parameter $\mathbfΔ$ as an informativeness measure and introduces strategic token arrangements to preserve sequential information flow.Extensive experiments demonstrate that MaMe achieves superior efficiency-performance trade-offs for both fine-tuned and off-the-shelf models. Particularly, our approach maintains robustness even under aggressive token reduction where existing methods undergo significant performance degradation.Beyond image classification, MaMe shows strong generalization capabilities across video and audio domains, establishing an effective approach for enhancing efficiency in diverse SSM applications.
title Towards Efficient Vision State Space Models via Token Merging
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.13599