Related papers: Swin3D: A Pretrained Transformer Backbone for 3D I…

Data diversity and abundance are essential for improving the performance and generalization of models in natural language processing and 2D vision. However, 3D vision domain suffers from the lack of 3D data, and simply combining multiple 3D…

Current popular backbones in computer vision, such as Vision Transformers (ViT) and ResNets are trained to perceive the world from 2D images. However, to more effectively understand 3D structural priors in 2D backbones, we propose Mask3D to…

Vision Transformers (ViT)s have shown great performance in self-supervised learning of global and local representations that can be transferred to downstream applications. Inspired by these results, we introduce a novel self-supervised…

3D Swin Transformer (3D-ST) known for its hierarchical attention and window-based processing, excels in capturing intricate spatial relationships within images. Spatial-spectral Transformer (SST), meanwhile, specializes in modeling…

In the field of medical images, although various works find Swin Transformer has promising effectiveness on pixelwise dense prediction, whether pre-training these models without using extra dataset can further boost the performance for the…

The existing deep learning fusion methods mainly concentrate on the convolutional neural networks, and few attempts are made with transformer. Meanwhile, the convolutional operation is a content-independent interaction between the image and…

We are witnessing a modeling shift from CNN to Transformers in computer vision. In this work, we present a self-supervised learning approach called MoBY, with Vision Transformers as its backbone architecture. The approach basically has no…

In oncology research, accurate 3D segmentation of lesions from CT scans is essential for the modeling of lesion growth kinetics. However, following the RECIST criteria, radiologists routinely only delineate each lesion on the axial slice…

Transformers have become a common foundation across deep learning, yet 3D scene understanding still relies on specialized backbones with strong domain priors. This keeps the field isolated from the broader Transformer ecosystem, limiting…

Remote sensing scene classification has been extensively studied for its critical roles in geological survey, oil exploration, traffic management, earthquake prediction, wildfire monitoring, and intelligence monitoring. In the past, the…

Deep learning has largely reshaped remote sensing (RS) research for aerial image understanding and made a great success. Nevertheless, most of the existing deep models are initialized with the ImageNet pretrained weights. Since natural…

Convolutional neural networks (CNNs) have been widely utilized in many computer vision tasks. However, CNNs have a fixed reception field and lack the ability of long-range perception, which is crucial to human pose estimation. Due to its…

In this paper, we aim to redesign the vision Transformer (ViT) as a new backbone to realize semantic image transmission, termed wireless image transmission transformer (WITT). Previous works build upon convolutional neural networks (CNNs),…

Sparse vision transformers have gained popularity as efficient encoders for medical volumetric segmentation, with Swin emerging as a prominent choice. Swin uses local attention to reduce complexity and yields excellent performance for many…

Recent advancements in large-scale Vision Transformers have made significant strides in improving pre-trained models for medical image segmentation. However, these methods face a notable challenge in acquiring a substantial amount of…

It is well believed that Transformer performs better in semantic segmentation compared to convolutional neural networks. Nevertheless, the original Vision Transformer may lack of inductive biases of local neighborhoods and possess a high…

Multivariate time series classification is of great importance in practical applications and is a challenging task. However, deep neural network models such as Transformers exhibit high accuracy in multivariate time series classification…

Dynamic magnetic resonance imaging (DMRI) is an effective imaging tool for diagnosis tasks that require motion tracking of a certain anatomy. To speed up DMRI acquisition, k-space measurements are commonly undersampled along spatial or…

Fast MRI aims to reconstruct a high fidelity image from partially observed measurements. Exuberant development in fast MRI using deep learning has been witnessed recently. Meanwhile, novel deep learning paradigms, e.g., Transformer based…

Accurate simulation of turbulent flows is fundamental to scientific and engineering applications. Direct numerical simulation (DNS) offers the highest fidelity but is computationally prohibitive, while existing data-driven alternatives…