Related papers: From Darkness to Detail: Frequency-Aware SSMs for …
UNet and its variants have been widely used in medical image segmentation. However, these models, especially those based on Transformer architectures, pose challenges due to their large number of parameters and computational loads, making…
The Transformer architecture has shown a remarkable ability in modeling global relationships. However, it poses a significant computational challenge when processing high-dimensional medical images. This hinders its development and…
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…
Low-light image enhancement is a crucial preprocessing task for some complex vision tasks. Target detection, image segmentation, and image recognition outcomes are all directly impacted by the impact of image enhancement. 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…
Remote sensing images are becoming increasingly widespread in military, earth resource exploration. Because of the limitation of a single sensor, we can obtain high spatial resolution grayscale panchromatic (PAN) images and low spatial…
Audio super-resolution aims to enhance low-resolution signals by creating high-frequency content. In this work, we modify the architecture of AERO (a state-of-the-art system for this task) for music super-resolution. SPecifically, we…
Recent advances in Vision Transformers (ViTs) and State Space Models (SSMs) have challenged the dominance of Convolutional Neural Networks (CNNs) in computer vision. ViTs excel at capturing global context, and SSMs like Mamba offer linear…
This paper presents a novel network structure with illumination-aware gamma correction and complete image modelling to solve the low-light image enhancement problem. Low-light environments usually lead to less informative large-scale dark…
Recent advancements in medical imaging have resulted in more complex and diverse images, with challenges such as high anatomical variability, blurred tissue boundaries, low organ contrast, and noise. Traditional segmentation methods…
The advent of Transformer and Mamba-based architectures has significantly advanced 3D medical image segmentation by enabling global contextual modeling, a capability traditionally limited in Convolutional Neural Networks (CNNs). However,…
Denoising is a crucial preprocessing step for hyperspectral images (HSIs) due to noise arising from intra-imaging mechanisms and environmental factors. Long-range spatial-spectral correlation modeling is beneficial for HSI denoising but…
Land cover analysis using hyperspectral images (HSI) remains an open problem due to their low spatial resolution and complex spectral information. Recent studies are primarily dedicated to designing Transformer-based architectures for…
For the deployment of neural networks in resource-constrained environments, prior works have built lightweight architectures with convolution and attention for capturing local and global dependencies, respectively. Recently, the state space…
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 highlatency inference. Striking a better balance between performance…
Mamba, with its selective State Space Models (SSMs), offers a more computationally efficient solution than Transformers for long-range dependency modeling. However, there is still a debate about its effectiveness in high-resolution 3D…
Spatial-Spectral Mamba (SSM) improves computational efficiency and captures long-range dependencies, addressing Transformer limitations. However, traditional Mamba models overlook rich spectral information in HSIs and struggle with high…
Due to the diverse geographical environments, intricate landscapes, and high-density settlements, the automatic identification of urban village boundaries using remote sensing images remains a highly challenging task. This paper proposes a…
The effectiveness and efficiency of modeling complex spectral-spatial relations are both crucial for Hyperspectral image (HSI) classification. Most existing methods based on CNNs and transformers still suffer from heavy computational…
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,…