Related papers: EfficientViM: Efficient Vision Mamba with Hidden S…
State-Space Models (SSMs) have attracted considerable attention in Image Restoration (IR) due to their ability to scale linearly sequence length while effectively capturing long-distance dependencies. However, deploying SSMs to edge devices…
State space models (SSMs) have emerged as an efficient alternative to Transformer models for language modeling, offering linear computational complexity and constant memory usage as context length increases. However, despite their…
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…
Online video super-resolution (VSR) is an important technique for many real-world video processing applications, which aims to restore the current high-resolution video frame based on temporally previous frames. Most of the existing online…
Food classification is the foundation for developing food vision tasks and plays a key role in the burgeoning field of computational nutrition. Due to the complexity of food requiring fine-grained classification, recent academic research…
Dynamic graphs exhibit intertwined spatio-temporal evolutionary patterns, widely existing in the real world. Nevertheless, the structure incompleteness, noise, and redundancy result in poor robustness for Dynamic Graph Neural Networks…
State Space Models (SSMs) have recently emerged as an alternative to Vision Transformers (ViTs) due to their unique ability of modeling global relationships with linear complexity. SSMs are specifically designed to capture spatially…
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,…
Depth map super-resolution technology aims to improve the spatial resolution of low-resolution depth maps and effectively restore high-frequency detail information. Traditional convolutional neural network has limitations in dealing with…
Within the family of convolutional neural networks, InceptionNeXt has shown excellent competitiveness in image classification and a number of downstream tasks. Built on parallel one-dimensional strip convolutions, however, it suffers from…
Modeling multivariate time series is a well-established problem with a wide range of applications from healthcare to financial markets. Traditional State Space Models (SSMs) are classical approaches for univariate time series modeling due…
State-space modeling has emerged as a powerful paradigm for sequence analysis in various tasks such as natural language processing, time-series forecasting, and signal processing. In this work, we propose an \emph{Adaptive State-Space…
Acquiring the road surface conditions in advance based on visual technologies provides effective information for the planning and control system of autonomous vehicles, thus improving the safety and driving comfort of the vehicles.…
Medical image segmentation plays an important role in various clinical applications; however, existing deep learning models face trade-offs between efficiency and accuracy. Convolutional Neural Networks (CNNs) capture local details well but…
Human activity recognition (HAR) on resource constrained devices requires high accuracy across diverse sensor setups. Selective state space models (SSMs) offer efficient linear time sequence processing, presenting a compelling alternative…
Multimodal fusion has made great progress in the field of remote sensing image classification due to its ability to exploit the complementary spatial-spectral information. Deep learning methods such as CNN and Transformer have been widely…
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…
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…
State Space Models (SSMs) have emerged as efficient alternatives to Transformers for sequential modeling, but their inability to leverage modality-specific features limits their performance in multi-modal pretraining. Here, we propose…
State Space Models (SSMs) have become serious contenders in the field of sequential modeling, challenging the dominance of Transformers. At the same time, Mixture of Experts (MoE) has significantly improved Transformer-based Large Language…