相关论文: Swin Deformable Attention U-Net Transformer (SDAUT…

This paper presents a new vision Transformer, called Swin Transformer, that capably serves as a general-purpose backbone for computer vision. Challenges in adapting Transformer from language to vision arise from differences between the two…

We introduce Gated-SwinRMT, a family of hybrid vision transformers that combine the shifted-window attention of the Swin Transformer with the Manhattan-distance spatial decay of Retentive Networks (RMT), augmented by input-dependent gating.…

Surface meshes are a favoured domain for representing structural and functional information on the human cortex, but their complex topology and geometry pose significant challenges for deep learning analysis. While Transformers have…

Blind-spot networks (BSN) have been prevalent neural architectures in self-supervised image denoising (SSID). However, most existing BSNs are conducted with convolution layers. Although transformers have shown the potential to overcome the…

Deep imitation learning is promising for solving dexterous manipulation tasks because it does not require an environment model and pre-programmed robot behavior. However, its application to dual-arm manipulation tasks remains challenging.…

Purpose: To propose a flexible and scalable imaging transformer (IT) architecture with three attention modules for multi-dimensional imaging data and apply it to MRI denoising with very low input SNR. Methods: Three independent attention…

We propose Diverse Restormer (DART), a novel image restoration method that effectively integrates information from various sources (long sequences, local and global regions, feature dimensions, and positional dimensions) to address…

Lumbar disc degeneration, a progressive structural wear and tear of lumbar intervertebral disc, is regarded as an essential role on low back pain, a significant global health concern. Automated lumbar spine geometry reconstruction from MR…

Transformer-based models have recently shown success in representation learning on graph-structured data beyond natural language processing and computer vision. However, the success is limited to small-scale graphs due to the drawbacks of…

Our research focuses on the critical field of early diagnosis of disease by examining retinal blood vessels in fundus images. While automatic segmentation of retinal blood vessels holds promise for early detection, accurate analysis remains…

Transformer is beneficial for image denoising tasks since it can model long-range dependencies to overcome the limitations presented by inductive convolutional biases. However, directly applying the transformer structure to remove noise is…

In both Computer Vision and the wider Deep Learning field, the Transformer architecture is well-established as state-of-the-art for many applications. For Multitask Learning, however, where there may be many more queries necessary compared…

Vision Transformers (ViTs) have achieved state-of-the-art performance in image classification, yet their attention mechanisms often remain opaque and exhibit dense, non-structured behaviors. In this work, we adapt our previously proposed…

The state-of-the-art speech enhancement has limited performance in speech estimation accuracy. Recently, in deep learning, the Transformer shows the potential to exploit the long-range dependency in speech by self-attention. Therefore, it…

Vision Transformer (ViT) has recently gained significant attention in solving computer vision (CV) problems due to its capability of extracting informative features and modeling long-range dependencies through the attention mechanism.…

Automated medical image segmentation can assist doctors to diagnose faster and more accurate. Deep learning based models for medical image segmentation have made great progress in recent years. However, the existing models fail to…

Scene text image super-resolution aims to increase the resolution and readability of the text in low-resolution images. Though significant improvement has been achieved by deep convolutional neural networks (CNNs), it remains difficult to…

The use of pretrained backbones with fine-tuning has been successful for 2D vision and natural language processing tasks, showing advantages over task-specific networks. In this work, we introduce a pretrained 3D backbone, called {\SST},…

Modeling spatiotemporal brain dynamics from high-dimensional data, such as functional Magnetic Resonance Imaging (fMRI), is a formidable task in neuroscience. Existing approaches for fMRI analysis utilize hand-crafted features, but the…

Complicated image registration is a key issue in medical image analysis, and deep learning-based methods have achieved better results than traditional methods. The methods include ConvNet-based and Transformer-based methods. Although…