English
Related papers

Related papers: Sequential Token Merging: Revisiting Hidden States

200 papers

Large language models (LLMs) face a daunting challenge due to the excessive computational and memory requirements of the commonly used Transformer architecture. While state space model (SSM) is a new type of foundational network…

Computation and Language · Computer Science 2024-03-06 Wei He , Kai Han , Yehui Tang , Chengcheng Wang , Yujie Yang , Tianyu Guo , Yunhe Wang

Selective state space models (SSM), such as Mamba, have gained prominence for their effectiveness in modeling sequential data. Despite their outstanding empirical performance, a comprehensive theoretical understanding of deep selective SSM…

Machine Learning · Computer Science 2025-03-10 Thieu N Vo , Tung D. Pham , Xin T. Tong , Tan Minh Nguyen

State Space Models (SSMs), especially recent Mamba architecture, have achieved remarkable success in sequence modeling tasks. However, extending SSMs to computer vision remains challenging due to the non-sequential structure of visual data…

Computer Vision and Pattern Recognition · Computer Science 2026-03-23 Puskal Khadka , KC Santosh

Multispectral fusion object detection is a critical task for edge-based maritime surveillance and remote sensing, demanding both high inference efficiency and robust feature representation for high-resolution inputs. However, current State…

Computer Vision and Pattern Recognition · Computer Science 2026-03-10 Qianqian Zhang , Leon Tabaro , Ahmed M. Abdelmoniem , Junshe An

Mamba, a State Space Model (SSM) that accelerates training by recasting recurrence as a parallel scan, has recently emerged as a linearly-scaling alternative to self-attention. Because of its unidirectional nature, each state in Mamba only…

Computer Vision and Pattern Recognition · Computer Science 2025-11-13 Jingwei Zhang , Xi Han , Hong Qin , Mahdi S. Hosseini , Dimitris Samaras

High-resolution remotely sensed images pose a challenge for commonly used semantic segmentation methods such as Convolutional Neural Network (CNN) and Vision Transformer (ViT). CNN-based methods struggle with handling such high-resolution…

Computer Vision and Pattern Recognition · Computer Science 2024-04-12 Qinfeng Zhu , Yuanzhi Cai , Yuan Fang , Yihan Yang , Cheng Chen , Lei Fan , Anh Nguyen

Recent learned image compression (LIC) leverages Mamba-style state-space models (SSMs) for global receptive fields with linear complexity. However, the standard Mamba adopts content-agnostic, predefined raster (or multi-directional) scans…

Computer Vision and Pattern Recognition · Computer Science 2026-03-18 Yunuo Chen , Zezheng Lyu , Bing He , Hongwei Hu , Qi Wang , Yuan Tian , Li Song , Wenjun Zhang , Guo Lu

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. Many subquadratic-time architectures such as linear attention,…

Machine Learning · Computer Science 2024-06-03 Albert Gu , Tri Dao

Selective state space models (SSMs), such as Mamba, achieve strong per-token expressivity by making the time discretization step $\Tilde{\Delta}$ a learned function of the input. However, in doing so, $\Tilde{\Delta}$ ceases to represent a…

Machine Learning · Computer Science 2026-05-12 Taylan Soydan , Miguel A. Bessa , Dirk Mohr , Rui Barreira

Video anomaly detection (VAD) has been extensively researched due to its potential for intelligent video systems. However, most existing methods based on CNNs and transformers still suffer from substantial computational burdens and have…

Computer Vision and Pattern Recognition · Computer Science 2024-12-31 Zhangxun Li , Mengyang Zhao , Xuan Yang , Yang Liu , Jiamu Sheng , Xinhua Zeng , Tian Wang , Kewei Wu , Yu-Gang Jiang

Remote sensing image fusion aims to generate a high-resolution multi/hyper-spectral image by combining a high-resolution image with limited spectral data and a low-resolution image rich in spectral information. Current deep learning (DL)…

Computer Vision and Pattern Recognition · Computer Science 2024-11-19 Siran Peng , Xiangyu Zhu , Haoyu Deng , Liang-Jian Deng , Zhen Lei

State-space models (SSMs) have recently shown promise in capturing long-range dependencies with subquadratic computational complexity, making them attractive for various applications. However, purely SSM-based models face critical…

Computer Vision and Pattern Recognition · Computer Science 2025-04-01 Abdelrahman Shaker , Syed Talal Wasim , Salman Khan , Juergen Gall , Fahad Shahbaz Khan

As remote sensing imaging technology continues to advance and evolve, processing high-resolution and diversified satellite imagery to improve segmentation accuracy and enhance interpretation efficiency emerg as a pivotal area of…

Computer Vision and Pattern Recognition · Computer Science 2024-10-10 Yice Cao , Chenchen Liu , Zhenhua Wu , Wenxin Yao , Liu Xiong , Jie Chen , Zhixiang Huang

Although MODIS time series data are critical for supporting dynamic, large-scale land cover land use classification, it is a challenging task to capture the subtle class signature information due to key MODIS difficulties, e.g., high…

Image and Video Processing · Electrical Eng. & Systems 2025-08-06 Zack Dewis , Zhengsen Xu , Yimin Zhu , Motasem Alkayid , Mabel Heffring , Lincoln Linlin Xu

Mamba has garnered widespread attention due to its flexible design and efficient hardware performance to process 1D sequences based on the state space model (SSM). Recent studies have attempted to apply Mamba to the visual domain by…

Computer Vision and Pattern Recognition · Computer Science 2024-10-15 Chengkun Wang , Wenzhao Zheng , Yuanhui Huang , Jie Zhou , Jiwen Lu

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 data and initial…

Computer Vision and Pattern Recognition · Computer Science 2024-08-16 Chenhongyi Yang , Zehui Chen , Miguel Espinosa , Linus Ericsson , Zhenyu Wang , Jiaming Liu , Elliot J. Crowley

In image fusion tasks, images from different sources possess distinct characteristics. This has driven the development of numerous methods to explore better ways of fusing them while preserving their respective characteristics.Mamba, as a…

Computer Vision and Pattern Recognition · Computer Science 2024-08-22 Zihan Cao , Xiao Wu , Liang-Jian Deng , Yu Zhong

Mamba-based vision models have gained extensive attention as a result of being computationally more efficient than attention-based models. However, spatial redundancy still exists in these models, represented by token and block redundancy.…

Computer Vision and Pattern Recognition · Computer Science 2025-04-08 Mengxuan Wu , Zekai Li , Zhiyuan Liang , Moyang Li , Xuanlei Zhao , Samir Khaki , Zheng Zhu , Xiaojiang Peng , Konstantinos N. Plataniotis , Kai Wang , Wangbo Zhao , Yang You

The realm of Mamba for vision has been advanced in recent years to strike for the alternatives of Vision Transformers (ViTs) that suffer from the quadratic complexity. While the recurrent scanning mechanism of Mamba offers computational…

Computer Vision and Pattern Recognition · Computer Science 2026-03-18 Masakazu Yoshimura , Teruaki Hayashi , Yuki Hoshino , Wei-Yao Wang , Takeshi Ohashi

Large pre-trained models have achieved outstanding results in sequence modeling. The Transformer block and its attention mechanism have been the main drivers of the success of these models. Recently, alternative architectures, such as…

Machine Learning · Computer Science 2025-01-29 J. Pablo Muñoz , Jinjie Yuan , Nilesh Jain