paper-with-me

홈 › Papers

DeMansia: Mamba Never Forgets Any Tokens

2024-08-04 · Ricky Fang

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

📄 PDF Abstract BibTeX arXiv:2408.01986

Code (1)

catalpaaa/demansia 공식 구현 pytorch

Tasks

image-classificationImage ClassificationMambaState Space Models

Methods 이 논문이 사용한 방법론

LV-ViT 설명 없음
Mamba Foundation models, now powering most of the exciting applications in deep learning, are almost universally based on the Transformer architecture and its core attention module.…

Similar Papers 제목 키워드 기반

ZigzagPointMamba: Spatial-Semantic Mamba for Point Cloud Understanding

2025-05-27 · Linshuang Diao, Dayong Ren, Sensen Song, Yurong Qian

State Space models (SSMs) such as PointMamba enable efficient feature extraction for point cloud self-supervised learning with linear complexity, outperforming Transformers in computational efficiency. However, existing …

Computational EfficiencyMambaSelf-Supervised LearningState Space Models

Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training

2024-12-17 · Mingjia Shi, Yuhao Zhou, Ruiji Yu, Zekai Li 외

Vision Mamba (e.g., Vim) has successfully been integrated into computer vision, and token reduction has yielded promising outcomes in Vision Transformers (ViTs). However, token reduction performs less effectively on Visi…

MambaToken Reduction

Spectral-Spatial Mamba for Hyperspectral Image Classification

2024-04-29 · Lingbo Huang, Yushi Chen, Xin He

Recently, deep learning models have achieved excellent performance in hyperspectral image (HSI) classification. Among the many deep models, Transformer has gradually attracted interest for its excellence in modeling the …

ClassificationComputational EfficiencyHyperspectral Image Classificationimage-classification+2

LoRA Learns Less and Forgets Less

2024-05-15 · Dan Biderman, Jacob Portes, Jose Javier Gonzalez Ortiz, Mansheej Paul 외

Low-Rank Adaptation (LoRA) is a widely-used parameter-efficient finetuning method for large language models. LoRA saves memory by training only low rank perturbations to selected weight matrices. In this work, we compare…

PlainMamba: Improving Non-Hierarchical Mamba in Visual Recognition

2024-03-26 · Chenhongyi Yang, Zehui Chen, Miguel Espinosa, Linus Ericsson 외

We present PlainMamba: a simple non-hierarchical state space model (SSM) designed for general visual recognition. The recent Mamba model has shown how SSMs can be highly competitive with other architectures on sequential…

Image ClassificationInstance SegmentationMambaobject-detection+2