Related papers: SegFormer3D: an Efficient Transformer for 3D Medic…

Current medical image segmentation approaches have limitations in deeply exploring multi-scale information and effectively combining local detail textures with global contextual semantic information. This results in over-segmentation,…

As a de facto solution, the vanilla Vision Transformers (ViTs) are encouraged to model long-range dependencies between arbitrary image patches while the global attended receptive field leads to quadratic computational cost. Another branch…

Although transformers have become the neural architectures of choice for natural language processing, they require orders of magnitude more training data, GPU memory, and computations in order to compete with convolutional neural networks…

Thermal weapon segmentation is crucial for surveillance and security applications, enabling robust detection under lowlight and visually obscured conditions where RGB-based systems fail. While convolutional neural networks (CNNs) dominate…

In recent years, vision transformers (ViTs) have emerged as powerful and promising techniques for computer vision tasks such as image classification, object detection, and segmentation. Unlike convolutional neural networks (CNNs), which…

State-of-the-art models for medical image segmentation achieve excellent accuracy but require substantial computational resources, limiting deployment in resource-constrained clinical settings. We present SegMate, an efficient 2.5D…

Transformers have emerged as viable alternatives to convolutional neural networks owing to their ability to learn non-local region relationships in the spatial domain. The self-attention mechanism of the transformer enables transformers to…

To obtain high-quality positron emission tomography (PET) images while minimizing radiation exposure, various methods have been proposed for reconstructing standard-dose PET (SPET) images from low-dose PET (LPET) sinograms directly.…

Existing computer vision research in categorization struggles with fine-grained attributes recognition due to the inherently high intra-class variances and low inter-class variances. SOTA methods tackle this challenge by locating the most…

Transformers have become one of the dominant architectures in deep learning, particularly as a powerful alternative to convolutional neural networks (CNNs) in computer vision. However, Transformer training and inference in previous works…

Casting semantic segmentation of outdoor LiDAR point clouds as a 2D problem, e.g., via range projection, is an effective and popular approach. These projection-based methods usually benefit from fast computations and, when combined with…

3D instance segmentation methods typically rely on high-quality point clouds or posed RGB-D scans, requiring complex multi-stage processing pipelines, and are highly sensitive to reconstruction noise. While recent feed-forward transformers…

Deep learning has been widely used in medical image segmentation and other aspects. However, the performance of existing medical image segmentation models has been limited by the challenge of obtaining sufficient high-quality labeled data…

Recently, transformer-based models have demonstrated remarkable performance on audio-visual segmentation (AVS) tasks. However, their expensive computational cost makes real-time inference impractical. By characterizing attention maps of the…

While CNNs were long considered state of the art for image processing, the introduction of Transformer architectures has challenged this position. While achieving excellent results in image classification and segmentation, Transformers…

Over the past two decades, machine analysis of medical imaging has advanced rapidly, opening up significant potential for several important medical applications. As complicated diseases increase and the number of cases rises, the role of…

Foundation models for interactive segmentation in 2D natural images and videos have sparked significant interest in building 3D foundation models for medical imaging. However, the domain gaps and clinical use cases for 3D medical imaging…

Accurate medical image segmentation is of utmost importance for enabling automated clinical decision procedures. However, prevailing supervised deep learning approaches for medical image segmentation encounter significant challenges due to…

The Vision Transformer (ViT) leverages the Transformer's encoder to capture global information by dividing images into patches and achieves superior performance across various computer vision tasks. However, the self-attention mechanism of…

Transformers have shown impressive performance in various natural language processing and computer vision tasks, due to the capability of modeling long-range dependencies. Recent progress has demonstrated that combining such Transformers…