Related papers: CvT: Introducing Convolutions to Vision Transforme…

It is a challenging task to learn discriminative representation from images and videos, due to large local redundancy and complex global dependency in these visual data. Convolution neural networks (CNNs) and vision transformers (ViTs) have…

Deep Convolutional Neural Networks (CNNs) have long been the architecture of choice for computer vision tasks. Recently, Transformer-based architectures like Vision Transformer (ViT) have matched or even surpassed ResNets for image…

Transformers, composed of multiple self-attention layers, hold strong promises toward a generic learning primitive applicable to different data modalities, including the recent breakthroughs in computer vision achieving state-of-the-art…

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…

The Transformer architecture has gained significant popularity in computer vision tasks due to its capacity to generalize and capture long-range dependencies. This characteristic makes it well-suited for generating spatiotemporal tokens…

This study evaluates the trade-offs between convolutional and transformer-based architectures on both medical and general-purpose image classification benchmarks. We use ResNet-18 as our baseline and introduce a fine-tuning strategy applied…

While convolutional neural networks (CNNs) and vision transformers (ViTs) have advanced medical image segmentation, they face inherent limitations such as local receptive fields in CNNs and high computational complexity in ViTs. This paper…

While models derived from Vision Transformers (ViTs) have been phonemically surging, pre-trained models cannot seamlessly adapt to arbitrary resolution images without altering the architecture and configuration, such as sampling the…

Vision Transformers (ViTs) are built by stacking independently parameterized blocks, but it remains unclear how much of this depth requires layer specific transformations and how much can be realized through recurrent computation. We study…

We introduce Contextual Vision Transformers (ContextViT), a method designed to generate robust image representations for datasets experiencing shifts in latent factors across various groups. Derived from the concept of in-context learning,…

Medical image segmentation plays a crucial role in various healthcare applications, enabling accurate diagnosis, treatment planning, and disease monitoring. Traditionally, convolutional neural networks (CNNs) dominated this domain,…

This paper tackles a significant challenge faced by Vision Transformers (ViTs): their constrained scalability across different image resolutions. Typically, ViTs experience a performance decline when processing resolutions different from…

Vision Transformers (ViTs) have emerged with superior performance on computer vision tasks compared to convolutional neural network (CNN)-based models. However, ViTs are mainly designed for image classification that generate single-scale…

We apply pre-trained architectures, originally developed for the ImageNet Large Scale Visual Recognition Challenge, for periocular recognition. These architectures have demonstrated significant success in various computer vision tasks…

Vision Transformer (ViT) architectures represent images as collections of high-dimensional vectorized tokens, each corresponding to a rectangular non-overlapping patch. This representation trades spatial granularity for embedding…

Dense computer vision tasks such as object detection and segmentation require effective multi-scale feature representation for detecting or classifying objects or regions with varying sizes. While Convolutional Neural Networks (CNNs) have…

While transformer architectures have dominated computer vision in recent years, these models cannot easily be deployed on hardware with limited resources for autonomous driving tasks that require real-time-performance. Their computational…

This decade is marked by the introduction of Vision Transformer, a radical paradigm shift in broad computer vision. A similar trend is followed in medical imaging, UNet, one of the most influential architectures, has been redesigned with…

Model binarization has made significant progress in enabling real-time and energy-efficient computation for convolutional neural networks (CNN), offering a potential solution to the deployment challenges faced by Vision Transformers (ViTs)…

Recently, vision transformers (ViTs) have superseded convolutional neural networks in numerous applications, including classification, detection, and segmentation. However, the high computational requirements of ViTs hinder their widespread…