paper-with-me

홈 › Papers

Famba-V: Fast Vision Mamba with Cross-Layer Token Fusion

2024-09-15 · Hui Shen, Zhongwei Wan, Xin Wang, Mi Zhang

Mamba and Vision Mamba (Vim) models have shown their potential as an alternative to methods based on Transformer architecture. This work introduces Fast Mamba for Vision (Famba-V), a cross-layer token fusion technique to enhance the training efficiency of Vim models. The key idea of Famba-V is to identify and fuse similar tokens across different Vim layers based on a suit of cross-layer strategies instead of simply applying token fusion uniformly across all the layers that existing works propose. We evaluate the performance of Famba-V on CIFAR-100. Our results show that Famba-V is able to enhance the training efficiency of Vim models by reducing both training time and peak memory usage during training. Moreover, the proposed cross-layer strategies allow Famba-V to deliver superior accuracy-efficiency trade-offs. These results all together demonstrate Famba-V as a promising efficiency enhancement technique for Vim models.

📄 PDF Abstract BibTeX arXiv:2409.09808

Code (1)

aiot-mlsys-lab/famba-v 공식 구현 pytorch

Tasks

Mamba

Methods 이 논문이 사용한 방법론

Attention 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
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.…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

DGFamba: Learning Flow Factorized State Space for Visual Domain Generalization

2025-04-10 · Qi Bi, Jingjun Yi, Hao Zheng, Haolan Zhan 외

Domain generalization aims to learn a representation from the source domain, which can be generalized to arbitrary unseen target domains. A fundamental challenge for visual domain generalization is the domain gap caused …

Domain Generalization

SparX: A Sparse Cross-Layer Connection Mechanism for Hierarchical Vision Mamba and Transformer Networks

2024-09-15 · Meng Lou, Yunxiang Fu, Yizhou Yu

Due to the capability of dynamic state space models (SSMs) in capturing long-range dependencies with linear-time computational complexity, Mamba has shown notable performance in NLP tasks. This has inspired the rapid dev…

Image ClassificationObject DetectionSemantic Segmentation

CrossMambaTuning: Synergistic Spatial and Cross-Layer Adaptation for Machine Vision Compression

2026-08-26 · Haobo Xiong, Shaobo Liu, Kai Liu, Chongyang Ding arxiv

To reduce deployment cost and retraining overhead, adapting pretrained learned image compression (LIC) models to downstream machine vision tasks has attracted growing attention. However, existing methods typically insert…

parameter-efficient fine-tuningImage Compression

MambaGlue: Fast and Robust Local Feature Matching With Mamba

2025-02-01 · Kihwan Ryoo, Hyungtae Lim, Hyun Myung

In recent years, robust matching methods using deep learning-based approaches have been actively studied and improved in computer vision tasks. However, there remains a persistent demand for both robust and fast matching…

Mamba

VADMamba: Exploring State Space Models for Fast Video Anomaly Detection

2025-03-27 · Jiahao Lyu, Minghua Zhao, Jing Hu, Xuewen Huang 외

Video anomaly detection (VAD) methods are mostly CNN-based or Transformer-based, achieving impressive results, but the focus on detection accuracy often comes at the expense of inference speed. The emergence of state spa…

Anomaly DetectionComputational EfficiencyLong-range modelingMamba+5