Related papers: MAP: Unleashing Hybrid Mamba-Transformer Vision Ba…

Recent Mamba-based architectures for video understanding demonstrate promising computational efficiency and competitive performance, yet struggle with overfitting issues that hinder their scalability. To overcome this challenge, we…

The vision community has started to build with the recently developed state space model, Mamba, as the new backbone for a range of tasks. This paper shows that Mamba's visual capability can be significantly enhanced through autoregressive…

Image generation models have encountered challenges related to scalability and quadratic complexity, primarily due to the reliance on Transformer-based backbones. In this study, we introduce MaskMamba, a novel hybrid model that combines…

Self-supervised pretraining is promising for large-scale neuroimaging, yet the impact of region-aware masking and hybrid sequence modeling remains underexplored. In this work, we introduce Rhamba, a region-aware pretraining framework that…

We propose a novel hybrid Mamba-Transformer backbone, MambaVision, specifically tailored for vision applications. Our core contribution includes redesigning the Mamba formulation to enhance its capability for efficient modeling of visual…

Transformer-based architectures have become the backbone of both uni-modal and multi-modal foundation models, largely due to their scalability via attention mechanisms, resulting in a rich ecosystem of publicly available pre-trained models…

We introduce a novel deep learning method for decoding error correction codes based on the Mamba architecture, enhanced with Transformer layers. Our approach proposes a hybrid decoder that leverages Mamba's efficient sequential modeling…

Cross-modal alignment is crucial for multimodal representation fusion due to the inherent heterogeneity between modalities. While Transformer-based methods have shown promising results in modeling inter-modal relationships, their quadratic…

The state space model Mamba has recently emerged as a promising paradigm in computer vision, attracting significant attention due to its efficient processing of long sequence tasks. Mamba's inherent causal mechanism renders it particularly…

Despite the remarkable quality of LLM-based text-to-speech systems, their reliance on autoregressive Transformers leads to quadratic computational complexity, which severely limits practical applications. Linear-time alternatives, notably…

Recently, the state space model Mamba has demonstrated efficient long-sequence modeling capabilities, particularly for addressing long-sequence visual tasks in 3D medical imaging. However, existing generative self-supervised learning…

Weakly supervised semantic segmentation offers a label-efficient solution to train segmentation models for volumetric medical imaging. However, existing approaches often rely on 2D encoders that neglect the inherent volumetric nature of the…

The use of self-supervised pre-training has emerged as a promising approach to enhance the performance of many different visual tasks. In this context, recent approaches have employed the Masked Image Modeling paradigm, which pre-trains a…

Transformers and Mamba, initially invented for natural language processing, have inspired backbone architectures for visual recognition. Recent studies integrated Local Attention Transformers with Mamba to capture both local details and…

U-shaped architectures have long dominated the field of medical image segmentation, while Transformers are widely employed for modeling long-range dependencies. The former typically handles scale variations implicitly by aggregating…

Linear modeling methods like Mamba have been merged as the effective backbone for the 3D object detection task. However, previous Mamba-based methods utilize the bidirectional encoding for the whole non-empty voxel sequence, which contains…

Recent efforts on image restoration have focused on developing "all-in-one" models that can handle different degradation types and levels within single model. However, most of mainstream Transformer-based ones confronted with dilemma…

Transformer-based methods have demonstrated remarkable capabilities in 3D semantic segmentation through their powerful attention mechanisms, but the quadratic complexity limits their modeling of long-range dependencies in large-scale point…

In this paper, we propose a self-prior guided Mamba-UNet network (SMamba-UNet) for medical image super-resolution. Existing methods are primarily based on convolutional neural networks (CNNs) or Transformers. CNNs-based methods fail to…

In recent years, Transformers-based models have made significant progress in the field of image restoration by leveraging their inherent ability to capture complex contextual features. Recently, Mamba models have made a splash in the field…