Saved in:
Bibliographic Details
Main Author: Fang, Ricky
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2408.01986
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910554919010304
author Fang, Ricky
author_facet Fang, Ricky
contents This paper examines the mathematical foundations of transformer architectures, highlighting their limitations particularly in handling long sequences. We explore prerequisite models such as Mamba, Vision Mamba (ViM), and LV-ViT that pave the way for our proposed architecture, DeMansia. DeMansia integrates state space models with token labeling techniques to enhance performance in image classification tasks, efficiently addressing the computational challenges posed by traditional transformers. The architecture, benchmark, and comparisons with contemporary models demonstrate DeMansia's effectiveness. The implementation of this paper is available on GitHub at https://github.com/catalpaaa/DeMansia
format Preprint
id arxiv_https___arxiv_org_abs_2408_01986
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle DeMansia: Mamba Never Forgets Any Tokens
Fang, Ricky
Computer Vision and Pattern Recognition
Artificial Intelligence
This paper examines the mathematical foundations of transformer architectures, highlighting their limitations particularly in handling long sequences. We explore prerequisite models such as Mamba, Vision Mamba (ViM), and LV-ViT that pave the way for our proposed architecture, DeMansia. DeMansia integrates state space models with token labeling techniques to enhance performance in image classification tasks, efficiently addressing the computational challenges posed by traditional transformers. The architecture, benchmark, and comparisons with contemporary models demonstrate DeMansia's effectiveness. The implementation of this paper is available on GitHub at https://github.com/catalpaaa/DeMansia
title DeMansia: Mamba Never Forgets Any Tokens
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2408.01986