Related papers: Diversity-enhanced Collaborative Mamba for Semi-su…
Medical time series are central to healthcare, enabling continuous monitoring and supporting timely clinical decisions. Despite recent progress, existing methods struggle to jointly model local-global dynamics and handle nonstationarities…
Perceptual image compression focuses on preserving high visual quality under low-bitrate constraints. Most existing approaches to perceptual compression leverage the strong generative capabilities of generative adversarial networks or…
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…
Semi-supervised learning has become increasingly popular in medical image segmentation due to its ability to leverage large amounts of unlabeled data to extract additional information. However, most existing semi-supervised segmentation…
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…
Image restoration requires simultaneously preserving fine-grained local structures and maintaining long-range spatial coherence. While convolutional networks struggle with limited receptive fields, and Transformers incur quadratic…
Although hyperspectral image (HSI) classification is critical for supporting various environmental applications, it is a challenging task due to the spectral-mixture effect, the spatial-spectral heterogeneity and the difficulty to preserve…
Semi-supervised learning has made significant strides in the medical domain since it alleviates the heavy burden of collecting abundant pixel-wise annotated data for semantic segmentation tasks. Existing semi-supervised approaches enhance…
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…
Accurate detection of cardiac abnormalities from electrocardiogram recordings is regarded as essential for clinical diagnostics and decision support. Traditional deep learning models such as residual networks and transformer architectures…
Multi-Modal Image Fusion (MMIF) aims to integrate complementary image information from different modalities to produce informative images. Previous deep learning-based MMIF methods generally adopt Convolutional Neural Networks (CNNs) or…
Recently, machine learning-based semantic segmentation algorithms have demonstrated their potential to accurately segment regions and contours in medical images, allowing the precise location of anatomical structures and abnormalities.…
Mamba-based architectures have shown to be a promising new direction for deep learning models owing to their competitive performance and sub-quadratic deployment speed. However, current Mamba multi-modal large language models (MLLM) are…
Image reflection separation aims to disentangle the transmission layer and the reflection layer from a blended image. Existing methods rely on limited information from a single image, tending to confuse the two layers when their contrasts…
We introduce a novel state-space architecture for diffusion models, effectively harnessing spatial and frequency information to enhance the inductive bias towards local features in input images for image generation tasks. While state-space…
Establishing semantic correspondences between images is a fundamental yet challenging task in computer vision. Traditional feature-metric methods enhance visual features but may miss complex inter-correlation relationships, while recent…
Meta-learning facilitates few-shot hyperspectral target detection (HTD), but adapting deep backbones remains challenging. Full-parameter fine-tuning is inefficient and prone to overfitting, and existing methods largely ignore the…
While supervised learning has achieved remarkable success, obtaining large-scale labeled datasets in biomedical imaging is often impractical due to high costs and the time-consuming annotations required from radiologists. Semi-supervised…
Deep learning methods, especially Convolutional Neural Networks (CNN) and Vision Transformer (ViT), are frequently employed to perform semantic segmentation of high-resolution remotely sensed images. However, CNNs are constrained by their…
State Space Models (SSM), such as Mamba, have shown strong representation ability in modeling long-range dependency with linear complexity, achieving successful applications from high-level to low-level vision tasks. However, SSM's…