Related papers: Surface Analysis with Vision Transformers

Confirming Alzheimer's disease (AD) typically relies on positron emission tomography (PET), which remains costly and invasive, motivating the use of structural MRI-based prescreening. Deep learning on non-Euclidean manifolds, particularly…

Neuroimaging of large populations is valuable to identify factors that promote or resist brain disease, and to assist diagnosis, subtyping, and prognosis. Data-driven models such as convolutional neural networks (CNNs) have increasingly…

We propose global context vision transformer (GC ViT), a novel architecture that enhances parameter and compute utilization for computer vision. Our method leverages global context self-attention modules, joint with standard local…

Convolutional neural networks (CNNs) and vision transformers (ViTs) have become essential in computer vision for local and global feature extraction. However, aggregating these architectures in existing methods often results in…

Human activity recognition is an emerging and important area in computer vision which seeks to determine the activity an individual or group of individuals are performing. The applications of this field ranges from generating highlight…

Due to its deficiency in prior knowledge (inductive bias), Vision Transformer (ViT) requires pre-training on large-scale datasets to perform well. Moreover, the growing layers and parameters in ViT models impede their applicability to…

The synergy of long-range dependencies from transformers and local representations of image content from convolutional neural networks (CNNs) has led to advanced architectures and increased performance for various medical image analysis…

Convolutional neural networks have enabled major progresses in addressing pixel-level prediction tasks such as semantic segmentation, depth estimation, surface normal prediction and so on, benefiting from their powerful capabilities in…

The advent of Vision Transformers (ViTs) marks a substantial paradigm shift in the realm of computer vision. ViTs capture the global information of images through self-attention modules, which perform dot product computations among…

Though vision transformers (ViTs) have achieved state-of-the-art performance in a variety of settings, they exhibit surprising failures when performing tasks involving visual relations. This begs the question: how do ViTs attempt to perform…

Self-supervised monocular depth estimation is an attractive solution that does not require hard-to-source depth labels for training. Convolutional neural networks (CNNs) have recently achieved great success in this task. However, their…

Vision Transformers (ViTs) have demonstrated strong performance across a range of computer vision tasks by modeling long-range spatial interactions via self-attention. However, channel-wise mixing in ViTs remains static, relying on fixed…

Recent self-supervised learning (SSL) methods have shown impressive results in learning visual representations from unlabeled images. This paper aims to improve their performance further by utilizing the architectural advantages of the…

Medical ultrasound (US) imaging has become a prominent modality for breast cancer imaging due to its ease-of-use, low-cost and safety. In the past decade, convolutional neural networks (CNNs) have emerged as the method of choice in vision…

Vision Transformer (ViT) architectures are becoming increasingly popular and widely employed to tackle computer vision applications. Their main feature is the capacity to extract global information through the self-attention mechanism,…

Given the significant advances in machine learning techniques on mobile devices, particularly in the domain of computer vision, in this work we quantitatively study the performance characteristics of 190 real-world vision transformers…

Convolutional neural networks (CNNs) are one of the most successful computer vision systems to solve object recognition. Furthermore, CNNs have major applications in understanding the nature of visual representations in the human brain. Yet…

Operator learning, which aims to approximate maps between infinite-dimensional function spaces, is an important area in scientific machine learning with applications across various physical domains. Here we introduce the Continuous Vision…

Convolutional Neural Networks (CNNs) have dominated computer vision for years, due to its ability in capturing locality and translation invariance. Recently, many vision transformer architectures have been proposed and they show promising…

Vision Transformers (ViT) have recently brought a new wave of research in the field of computer vision. These models have performed particularly well in image classification and segmentation. Research on semantic and instance segmentation…