Results 171 to 180 of about 13,981 (216)

Graph-Mamba: Towards Long-Range Graph Sequence Modeling with Selective State Spaces

arXiv.org
Attention mechanisms have been widely used to capture long-range dependencies among nodes in Graph Transformers. Bottlenecked by the quadratic computational cost, attention mechanisms fail to scale in large graphs.
Chloe Wang, Oleksii Tsepa, Jun Ma, Bo Wang   +3 more
semanticscholar   +1 more source

LongMamba: Enhancing Mamba's Long-Context Capabilities via Training-Free Receptive Field Enlargement

International Conference on Learning Representations
State space models (SSMs) have emerged as an efficient alternative to Transformer models for language modeling, offering linear computational complexity and constant memory usage as context length increases.
Zhifan Ye, Kejing Xia, Yonggan Fu, Xin Dong, Jihoon Hong, Xiangchi Yuan, Shizhe Diao, Jan Kautz, Pavlo Molchanov, Yingyan Lin   +9 more
semanticscholar   +1 more source

VM-UNET-V2 Rethinking Vision Mamba UNet for Medical Image Segmentation

arXiv.org
In the field of medical image segmentation, models based on both CNN and Transformer have been thoroughly investigated. However, CNNs have limited modeling capabilities for long-range dependencies, making it challenging to exploit the semantic ...
Mingya Zhang, Yue Yu, Limei Gu, Tingsheng Lin, Xianping Tao   +4 more
semanticscholar   +1 more source

MDNet: Mamba-Effective Diffusion-Distillation Network for RGB-Thermal Urban Dense Prediction

IEEE transactions on circuits and systems for video technology (Print)
In recent years, significant progress has been achieved in urban dense prediction tasks, particularly with advancements in deep learning models and novel architectures that enhance segmentation accuracy and computational efficiency.
Wujie Zhou, Hongping Wu, Qiuping Jiang
semanticscholar   +1 more source

JamMa: Ultra-lightweight Local Feature Matching with Joint Mamba

Computer Vision and Pattern Recognition
Existing state-of-the-art feature matchers capture long-range dependencies with Transformers but are hindered by high spatial complexity, leading to demanding training and high-latency inference.
Xiaoyong Lu, Songlin Du
semanticscholar   +1 more source

ZigMa: A DiT-style Zigzag Mamba Diffusion Model

European Conference on Computer Vision
The diffusion model has long been plagued by scalability and quadratic complexity issues, especially within transformer-based structures. In this study, we aim to leverage the long sequence modeling capability of a State-Space Model called Mamba to ...
Vincent Tao Hu, Stefan Andreas Baumann, Ming Gui, O. Grebenkova, Pingchuan Ma, Johannes S. Fischer, Bjorn Ommer   +6 more
semanticscholar   +1 more source

Fusion-Mamba for Cross-Modality Object Detection

IEEE transactions on multimedia
Cross-modality object detection aims to fuse complementary information from different modalities to improve model performance, which achieves a wider range of applications.
Wenhao Dong, Haodong Zhu, Shaohui Lin, Xiaoyan Luo, Yunhang Shen, Guodong Guo, Baochang Zhang   +6 more
semanticscholar   +1 more source

HSI-MFormer: Integrating Mamba and Transformer Experts for Hyperspectral Image Classification

IEEE Transactions on Geoscience and Remote Sensing
Hyperspectral image (HSI) classification is fundamental to numerous remote sensing applications, enabling detailed analysis of material properties and environmental conditions.
Yan He, Bing Tu, Bo Liu, Jun Li, A. Plaza   +4 more
semanticscholar   +1 more source

Visually Stabilized Mamba U-Shaped Network With Strong Inductive Bias for 3-D Brain Tumor Segmentation

IEEE Transactions on Instrumentation and Measurement
Multimodal magnetic resonance imaging (MRI) plays a crucial role in the precise segmentation of brain tumors, which is essential for clinical quantitative assessment, diagnostic processes, and treatment strategy planning.
Zhiqin Zhu, Zhandong Wang, Guanqiu Qi, Yuanxiang Zhao, Yu Liu   +4 more
semanticscholar   +1 more source

Shrinkage mamba relation network with out-of-distribution data augmentation for rotating machinery fault detection and localization under zero-faulty data

Mechanical systems and signal processing
Zuoyi Chen, Hong-Zhong Huang, Zhongwei Deng, Jun Wu   +3 more
semanticscholar   +1 more source