paper-with-me

Papers

Adventurer: Optimizing Vision Mamba Architecture Designs for Efficiency

2025-01-01 · CVPR 2025 1 · Feng Wang, Timing Yang, Yaodong Yu, Sucheng Ren, Guoyizhe Wei, Angtian Wang, Wei Shao, Yuyin Zhou, Alan Yuille, Cihang Xie

In this work, we introduce the Adventurer series models where we treat images as sequences of patch tokens and employ uni-directional language models to learn visual representations. This modeling paradigm allows us to process images in a recurrent formulation with linear complexity relative to the sequence length, which can effectively address the memory and computation explosion issues posed by high-resolution and fine-grained images. In detail, we introduce two simple designs that seamlessly integrate image inputs into the causal inference framework: a global pooling token placed at the beginning of the sequence and a flipping operation between every two layers. Extensive empirical studies highlight that compared with the existing plain architectures such as DeiT and Vim, Adventurer offers an optimal efficiency-accuracy trade-off. For example, our Adventurer-Base attains a competitive test accuracy of 84.3% on the standard ImageNet-1k benchmark with 216 images/s training throughput, which is 3.8x and 6.2x faster than Vim and DeiT to achieve the same result. As Adventurer offers great computation and memory efficiency and allows scaling with linear complexity, we hope this architecture can benefit future explorations in modeling long sequences for high-resolution or fine-grained images.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Causal InferenceMamba

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
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…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
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 $x$…
Feedforward Network A Feedforward Network, or a Multilayer Perceptron (MLP), is a neural network with solely densely connected layers. This is the classic neural network architecture of the…
Causal inference Causal inference is the process of drawing a conclusion about a causal connection based on the conditions of the occurrence of an effect. The main difference between causal…

Similar Papers 제목 키워드 기반

A Survey on Mamba Architecture for Vision Applications

2025-02-11 · Fady Ibrahim, Guangjun Liu, Guanghui Wang

Transformers have become foundational for visual tasks such as object detection, semantic segmentation, and video understanding, but their quadratic complexity in attention mechanisms presents scalability challenges. To …

Mambaobject-detectionObject DetectionPosition+4

Causal Image Modeling for Efficient Visual Understanding

2024-10-10 · Feng Wang, Timing Yang, Yaodong Yu, Sucheng Ren 외

In this work, we present a comprehensive analysis of causal image modeling and introduce the Adventurer series models where we treat images as sequences of patch tokens and employ uni-directional language models to learn…

Causal Inference

Falcon Mamba: The First Competitive Attention-free 7B Language Model

2024-10-07 · Jingwei Zuo, Maksim Velikanov, Dhia Eddine Rhaiem, Ilyas Chahed 외

In this technical report, we present Falcon Mamba 7B, a new base large language model based on the novel Mamba architecture. Falcon Mamba 7B is trained on 5.8 trillion tokens with carefully selected data mixtures. As a p…

Language ModelingLanguage ModellingLarge Language ModelMamba

DSVM-UNet : Enhancing VM-UNet with Dual Self-distillation for Medical Image Segmentation

2026-01-27 · Renrong Shao, Dongyang Li, Dong Xia, Lin Shao 외 arxiv

Vision Mamba models have been extensively researched in various fields, which address the limitations of previous models by effectively managing long-range dependencies with a linear-time overhead. Several prospective st…

Medical Image SegmentationComputational Efficiency

Parameter Efficient Mamba Tuning via Projector-targeted Diagonal-centric Linear Transformation

2024-11-21 · CVPR 2025 1 · Seokil Ham, Hee-Seon Kim, Sangmin Woo, Changick Kim

Despite the growing interest in Mamba architecture as a potential replacement for Transformer architecture, parameter-efficient fine-tuning (PEFT) approaches for Mamba remain largely unexplored. In our study, we introduc…

Mambaparameter-efficient fine-tuningState Space ModelsTransfer Learning