Related papers: EAMamba: Efficient All-Around Vision State Space M…

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…

We introduce LocoMamba, a vision-driven cross-modal DRL framework built on selective state-space models, specifically leveraging Mamba, that achieves near-linear-time sequence modeling, effectively captures long-range dependencies, and…

This paper introduces VMatcher, a hybrid Mamba-Transformer network for semi-dense feature matching between image pairs. Learning-based feature matching methods, whether detector-based or detector-free, achieve state-of-the-art performance…

Radiography imaging protocols target on specific anatomical regions, resulting in highly consistent images with recurrent structural patterns across patients. Recent advances in medical anomaly detection have demonstrated the effectiveness…

In endoscopic imaging, the recorded images are prone to exposure abnormalities, so maintaining high-quality images is important to assist healthcare professionals in performing decision-making. To overcome this issue, We design a…

Currently, Transformer is the most popular architecture for image dehazing, but due to its large computational complexity, its ability to handle long-range dependency is limited on resource-constrained devices. To tackle this challenge, we…

Generative Artificial Intelligence (AI) has gained significant attention in recent years, revolutionizing various applications across industries. Among these, advanced vision models for image super-resolution are in high demand,…

AI-powered medical devices have driven the need for real-time, on-device inference such as biomedical image classification. Deployment of deep learning models at the edge is now used for applications such as anomaly detection and…

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 techniques. To…

Capturing long-range dependencies (LRD) efficiently is a core challenge in visual recognition, and state-space models (SSMs) have recently emerged as a promising alternative to self-attention for addressing it. However, adapting SSMs into…

Recently, polarimetric synthetic aperture radar (PolSAR) image classification has been greatly promoted by deep neural networks. However,current deep learning-based PolSAR classification methods encounter difficulties due to its dependence…

Recent progress in image restoration has underscored Spatial State Models (SSMs) as powerful tools for modeling long-range dependencies, owing to their appealing linear complexity and computational efficiency. However, SSM-based approaches…

In recent years, computer vision has witnessed remarkable progress, fueled by the development of innovative architectures such as Convolutional Neural Networks (CNNs), Generative Adversarial Networks (GANs), diffusion-based architectures,…

Accurate medical image segmentation demands the integration of multi-scale information, spanning from local features to global dependencies. However, it is challenging for existing methods to model long-range global information, where…

Convolutional neural networks have primarily led 3D medical image segmentation but may be limited by small receptive fields. Transformer models excel in capturing global relationships through self-attention but are challenged by high…

Recently, the state space model (SSM) represented by Mamba has shown remarkable performance in long-term sequence modeling tasks, including speech enhancement. However, due to substantial differences in sub-band features, applying the same…

Transformers have become one of the foundational architectures in point cloud analysis tasks due to their excellent global modeling ability. However, the attention mechanism has quadratic complexity, making the design of a linear complexity…

Modeling daily hand interactions often struggles with severe occlusions, such as when two hands overlap, which highlights the need for robust feature learning in 3D hand pose estimation (HPE). To handle such occluded hand images, it is…

Semantic segmentation is a vital task in the field of remote sensing (RS). However, conventional convolutional neural network (CNN) and transformer-based models face limitations in capturing long-range dependencies or are often…

Image segmentation holds a vital position in the realms of diagnosis and treatment within the medical domain. Traditional convolutional neural networks (CNNs) and Transformer models have made significant advancements in this realm, but they…