相关论文: Mamba-FETrack: Frame-Event Tracking via State Spac…
Current RGBT tracking methods often overlook the impact of fusion location on mitigating modality gap, which is key factor to effective tracking. Our analysis reveals that shallower fusion yields smaller distribution gap. However, the…
Cross-modality fusing complementary information from different modalities effectively improves object detection performance, making it more useful and robust for a wider range of applications. Existing fusion strategies combine different…
State Space Model (SSM) is a mathematical model used to describe and analyze the behavior of dynamic systems. This model has witnessed numerous applications in several fields, including control theory, signal processing, economics and…
Background: High-resolution MRI is critical for diagnosis, but long acquisition times limit clinical use. Super-resolution (SR) can enhance resolution post-scan, yet existing deep learning methods face fidelity-efficiency trade-offs.…
Spatial-Temporal Graph (STG) data is characterized as dynamic, heterogenous, and non-stationary, leading to the continuous challenge of spatial-temporal graph learning. In the past few years, various GNN-based methods have been proposed to…
Selective state space models (SSMs), such as Mamba, highly excel at capturing long-range dependencies in 1D sequential data, while their applications to 2D vision tasks still face challenges. Current visual SSMs often convert images into 1D…
With the explosive growth of data, long-sequence modeling has become increasingly important in tasks such as natural language processing and bioinformatics. However, existing methods face inherent trade-offs between efficiency and memory.…
Mamba has demonstrated exceptional performance in visual tasks due to its powerful global modeling capabilities and linear computational complexity, offering considerable potential in hyperspectral image super-resolution (HSISR). However,…
We introduce a novel end-to-end framework for jet reconstruction in high-energy collider events, leveraging the efficiency and long-range modeling capabilities of the Mamba architecture. Our model unifies instance segmentation,…
Recent advances in sequence modeling have introduced selective SSMs as promising alternatives to Transformer architectures, offering theoretical computational efficiency and sequence processing advantages. A comprehensive understanding of…
Multimodal image fusion aims to integrate information from different imaging techniques to produce a comprehensive, detail-rich single image for downstream vision tasks. Existing methods based on local convolutional neural networks (CNNs)…
While the conditional sequence modeling with the transformer architecture has demonstrated its effectiveness in dealing with offline reinforcement learning (RL) tasks, it is struggle to handle out-of-distribution states and actions.…
Sequential modeling has demonstrated remarkable capabilities in offline reinforcement learning (RL), with Decision Transformer (DT) being one of the most notable representatives, achieving significant success. However, RL trajectories…
Recently, Mamba-based methods, with its advantage in long-range information modeling and linear complexity, have shown great potential in optimizing both computational cost and performance of light field image super-resolution (LFSR).…
Cracks pose safety risks to infrastructure and cannot be overlooked. The prevailing structures in existing crack segmentation networks predominantly consist of CNNs or Transformers. However, CNNs exhibit a deficiency in global modeling…
The typical Selective State-Space Model (SSM) used in Mamba addresses several limitations of Transformers, such as the quadratic computational complexity with respect to sequence length and the significant memory requirements during…
Similar to Vision Transformers, this paper identifies artifacts also present within the feature maps of Vision Mamba. These artifacts, corresponding to high-norm tokens emerging in low-information background areas of images, appear much…
Model-based reinforcement learning (RL) offers a solution to the data inefficiency that plagues most model-free RL algorithms. However, learning a robust world model often requires complex and deep architectures, which are computationally…
The growing demand for efficient long-sequence modeling on edge devices has propelled widespread adoption of State Space Models (SSMs) like Mamba, due to their superior computational efficiency and scalability. As its autoregressive…
Traditionally for improving the segmentation performance of models, most approaches prefer to use adding more complex modules. And this is not suitable for the medical field, especially for mobile medical devices, where computationally…