Related papers: SegMaFormer: A Hybrid State-Space and Transformer …
Convolutional Neural Networks (CNNs) and Transformer-based self-attention models have become the standard for medical image segmentation. This paper demonstrates that convolution and self-attention, while widely used, are not the only…
State Space Models (SSMs), especially recent Mamba architecture, have achieved remarkable success in sequence modeling tasks. However, extending SSMs to computer vision remains challenging due to the non-sequential structure of visual data…
Accurate medical image segmentation is an integral part of the medical image analysis pipeline that requires the ability to merge local and global information. While vision transformers are able to capture global interactions using vanilla…
Radiography imaging protocols target on specific anatomical regions, resulting in highly consistent images with recurrent structural patterns across patients. Recent advances in medical anomaly detection have demonstrated the effectiveness…
Deep learning has been widely applied to 3D medical image segmentation tasks. However, due to the diversity of imaging modalities, the high-dimensional nature of the data, and the heterogeneity of anatomical structures, achieving both…
Medical image segmentation has traditionally relied on convolutional neural networks (CNNs) and Transformer-based models. CNNs, however, are constrained by limited receptive fields, while Transformers face scalability challenges due to…
Hyperspectral image (HSI) classification remains challenging due to high spectral dimensionality, redundancy, and limited labeled data. Although convolutional neural networks (CNNs) and Vision Transformers (ViTs) achieve strong performance…
Dynamic graph embedding has emerged as an important technique for modeling complex time-evolving networks across diverse domains. While transformer-based models have shown promise in capturing long-range dependencies in temporal graph data,…
Multi-modal medical image synthesis involves nonlinear transformation of tissue signals between source and target modalities, where tissues exhibit contextual interactions across diverse spatial distances. As such, the utility of a network…
State space models (SSMs) with selection mechanisms and hardware-aware architectures, namely Mamba, have recently demonstrated significant promise in long-sequence modeling. Since the self-attention mechanism in transformers has quadratic…
Deep learning-based single-channel speaker separation has improved significantly in recent years largely due to the introduction of the transformer-based attention mechanism. However, these improvements come at the expense of intense…
Feature encoders play a key role in pixel-level crack segmentation by shaping the representation of fine textures and thin structures. Existing CNN-, Transformer-, and Mamba-based models each capture only part of the required spatial or…
Integrating components from convolutional neural networks and state space models in medical image segmentation presents a compelling approach to enhance accuracy and efficiency. We introduce Mamba HUNet, a novel architecture tailored for…
Prior efforts in light-weight model development mainly centered on CNN and Transformer-based designs yet faced persistent challenges. CNNs adept at local feature extraction compromise resolution while Transformers offer global reach but…
Transformers have revolutionized deep learning across various tasks, including audio representation learning, due to their powerful modeling capabilities. However, they often suffer from quadratic complexity in both GPU memory usage and…
Semantic segmentation of high-resolution remote sensing images is vital in downstream applications such as land-cover mapping, urban planning and disaster assessment.Existing Transformer-based methods suffer from the constraint between…
The goal of style transfer is, given a content image and a style source, generating a new image preserving the content but with the artistic representation of the style source. Most of the state-of-the-art architectures use transformers or…
Convolutional neural networks and Transformer have made significant progresses in multi-modality medical image super-resolution. However, these methods either have a fixed receptive field for local learning or significant computational…
Recently, deep learning models have achieved excellent performance in hyperspectral image (HSI) classification. Among the many deep models, Transformer has gradually attracted interest for its excellence in modeling the long-range…
Decision Transformer, a promising approach that applies Transformer architectures to reinforcement learning, relies on causal self-attention to model sequences of states, actions, and rewards. While this method has shown competitive…