Related papers: MedConv: Convolutions Beat Transformers on Long-Ta…

Convolutional neural networks (CNNs) have been the consensus for medical image segmentation tasks. However, they suffer from the limitation in modeling long-range dependencies and spatial correlations due to the nature of convolution…

The paper introduces the weighted convolution, a novel approach to the convolution for signals defined on regular grids (e.g., 2D images) through the application of an optimal density function to scale the contribution of neighbouring…

The high demand for computational and storage resources severely impede the deployment of deep convolutional neural networks (CNNs) in limited-resource devices. Recent CNN architectures have proposed reduced complexity versions (e.g.…

Recent studies have witnessed the effectiveness of 3D convolutions on segmenting volumetric medical images. Compared with the 2D counterparts, 3D convolutions can capture the spatial context in three dimensions. Nevertheless, models…

Transformer has achieved competitive performance against state-of-the-art end-to-end models in automatic speech recognition (ASR), and requires significantly less training time than RNN-based models. The original Transformer, with…

Gastrointestinal cancer is a leading cause of cancer-related incidence and death, making it crucial to develop novel computer-aided diagnosis systems for early detection and enhanced treatment. Traditional approaches rely on the expertise…

Object detection has made substantial progress in the last decade, due to the capability of convolution in extracting local context of objects. However, the scales of objects are diverse and current convolution can only process single-scale…

Dynamic convolution achieves better performance for efficient CNNs at the cost of negligible FLOPs increase. However, the performance increase can not match the significantly expanded number of parameters, which is the main bottleneck in…

Global convolutions have shown increasing promise as powerful general-purpose sequence models. However, training long convolutions is challenging, and kernel parameterizations must be able to learn long-range dependencies without…

Medical image analysis is a hot research topic because of its usefulness in different clinical applications, such as early disease diagnosis and treatment. Convolutional neural networks (CNNs) have become the de-facto standard in medical…

Computer Tomography (CT) images have become quite important to diagnose diseases. CT scan slice contains a vast amount of data that may not be properly examined with the requisite precision and speed using normal visual inspection. A…

Purpose: The distribution of visceral adipose tissue (VAT) in cystectomy patients is indicative of the incidence of post-operative complications. Existing VAT segmentation methods for computed tomography (CT) employing intensity…

Early diagnosis of treatable diseases is essential for improving healthcare, and many diseases' onsets are predictable from annual lab tests and their temporal trends. We introduce a multi-resolution convolutional neural network for early…

Convolutional neural networks (CNNs) are essential tools for computer vision tasks, but they lack traditionally desired properties of extracted features that could further improve model performance, e.g., rotational equivariance. Such…

Image-to-image translation models have achieved notable success in converting images across visual domains and are increasingly used for medical tasks such as predicting post-operative outcomes and modeling disease progression. However,…

In this work, we propose a new solution to 3D human pose estimation in videos. Instead of directly regressing the 3D joint locations, we draw inspiration from the human skeleton anatomy and decompose the task into bone direction prediction…

Over the past decade, Deep Convolutional Neural Networks have been widely adopted for medical image segmentation and shown to achieve adequate performance. However, due to the inherent inductive biases present in the convolutional…

Land Use Scene Classification (LUSC) from remote sensing imagery plays a critical role in environmental monitoring, urban planning, and sustainable resource management. In recent years, deep learning methods have significantly advanced the…

Objective: The aim of this study was to systematically evaluate and compare the performance of five state-of-the-art transformer-based architectures - Vision Transformer (ViT), Data-efficient Image Transformer (DeiT), ConvNeXt, Swin…

The fast growing deep learning technologies have become the main solution of many machine learning problems for medical image analysis. Deep convolution neural networks (CNNs), as one of the most important branch of the deep learning…