Related papers: Mamba Learns in Context: Structure-Aware Domain Ge…
Multi-task dense scene understanding, which trains a model for multiple dense prediction tasks, has a wide range of application scenarios. Capturing long-range dependency and enhancing cross-task interactions are crucial to multi-task dense…
Understanding the inter-relations and interactions between tasks is crucial for multi-task dense prediction. Existing methods predominantly utilize convolutional layers and attention mechanisms to explore task-level interactions. In this…
In the realm of time series forecasting (TSF), it is imperative for models to adeptly discern and distill hidden patterns within historical time series data to forecast future states. Transformer-based models exhibit formidable efficacy in…
State Space Models (SSMs) have emerged as promising alternatives to attention mechanisms, with the Mamba architecture demonstrating impressive performance and linear complexity for processing long sequences. However, the fundamental…
Recently, the Mamba architecture based on State Space Models (SSMs) has gained attention in 3D human pose estimation due to its linear complexity and strong global modeling capability. However, existing SSM-based methods typically apply…
Mamba is a newly proposed architecture which behaves like a recurrent neural network (RNN) with attention-like capabilities. These properties are promising for speaker diarization, as attention-based models have unsuitable memory…
Existing deraining Transformers employ self-attention mechanisms with fixed-range windows or along channel dimensions, limiting the exploitation of non-local receptive fields. In response to this issue, we introduce a novel dual-branch…
Deep learning, particularly convolutional neural networks (CNNs) and Transformers, has significantly advanced 3D medical image segmentation. While CNNs are highly effective at capturing local features, their limited receptive fields may…
Structured state space models' (SSMs) development in recent studies, such as Mamba and Mamba2, outperformed and solved the computational inefficiency of transformers and large language models at small to medium scale. In this work, we…
Traffic image restoration under adverse weather conditions remains a critical challenge for intelligent transportation systems. Existing methods primarily focus on spatial-domain modeling but neglect frequency-domain priors. Although the…
Semi-supervised domain adaptation (SSDA) adapts a learner to a new domain by effectively utilizing source domain data and a few labeled target samples. It is a practical yet under-investigated research topic. In this paper, we analyze the…
Image super-resolution (SR) is a critical technology for overcoming the inherent hardware limitations of sensors. However, existing approaches mainly focus on directly enhancing the final resolution, often neglecting effective control over…
Multimodal Sentiment Analysis (MSA) requires effective modeling of cross-modal interactions and contextual dependencies while remaining computationally efficient. Existing fusion approaches predominantly rely on Transformer-based…
In recent years, deep learning has shown near-expert performance in segmenting complex medical tissues and tumors. However, existing models are often task-specific, with performance varying across modalities and anatomical regions.…
Change detection in remote sensing images is an essential tool for analyzing a region at different times. It finds varied applications in monitoring environmental changes, man-made changes as well as corresponding decision-making and…
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…
Motion forecasting is a crucial component of autonomous driving systems, enabling the generation of accurate and smooth future trajectories to ensure safe navigation to the destination. In previous methods, potential future trajectories are…
Salient object detection (SOD) requires modeling both long-range contextual dependencies and fine-grained structural details, which remains challenging for convolutional, transformer-based, and Mamba-based state space models. While recent…
Hyperspectral image (HSI) classification constitutes the fundamental research in remote sensing fields. Convolutional Neural Networks (CNNs) and Transformers have demonstrated impressive capability in capturing spectral-spatial contextual…
State space models have shown significant promise in Natural Language Processing (NLP) and, more recently, computer vision. This paper introduces a new methodology leveraging Mamba and Masked Autoencoder networks for point cloud data in…