Transformers have demonstrated impressive expressiveness and transfer capability in
computer vision fields. Dense prediction is a fundamental problem in computer vision that is …

As the core building block of vision transformers, attention is a powerful tool to capture long-
range dependency. However, such power comes at a cost: it incurs a huge computation …

Transformers have recently shown superior performances on various vision tasks. The large,
sometimes even global, receptive field endows Transformer models with higher …

Vision transformers have become popular as a possible substitute to convolutional neural
networks (CNNs) for a variety of computer vision applications. These transformers, with their …

The dynamic neural network (DNN), in contrast to the static counterpart, offers numerous
advantages, such as improved accuracy, efficiency, and interpretability. These benefits stem …

Recent transformer-based models, especially patch-based methods, have shown huge
potentiality in vision tasks. However, the split fixed-size patches divide the input features into …

Window-based attention has become a popular choice in vision transformers due to its
superior performance, lower computational complexity, and less memory footprint. However …

Panoramic images with their 360deg directional view encompass exhaustive information
about the surrounding space, providing a rich foundation for scene understanding. To unfold …

Patch attacks, one of the most threatening forms of physical attack in adversarial examples,
can lead networks to induce misclassification by modifying pixels arbitrarily in a continuous …

State-of-the-art parametric and non-parametric style transfer approaches are prone to either
distorted local style patterns due to global statistics alignment, or unpleasing artifacts …