Related papers: Application of Integral Value Transformation (IVT)…

Recently, vision transformers (ViTs) have superseded convolutional neural networks in numerous applications, including classification, detection, and segmentation.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…

This paper proposes a working recipe of using Vision Transformer (ViT) in class incremental learning. Although this recipe only combines existing techniques, developing the combination is not trivial. Firstly, naive application of ViT to…

Deep neural networks are applied in more and more areas of everyday life. However, they still lack essential abilities, such as robustly dealing with spatially transformed input signals. Approaches to mitigate this severe robustness issue…

Over the past decade, various matrix completion algorithms have been developed. Thresholded singular value decomposition (SVD) is a popular technique in implementing many of them. A sizable number of studies have shown its theoretical and…

Recent advancements in computer vision have highlighted the scalability of Vision Transformers (ViTs) across various tasks, yet challenges remain in balancing adaptability, computational efficiency, and the ability to model higher-order…

One of the most common ways to represent and share visual designs is with vector graphics. Designers working with vector graphics often explore layout alternatives and generate them by moving and resizing elements. The motivation for this…

Vision Transformers (ViTs) have achieved remarkable success over various vision tasks, yet their robustness against data distribution shifts and inherent inductive biases remain underexplored. To enhance the robustness of ViT models for…

We present in this paper a new architecture, named Convolutional vision Transformer (CvT), that improves Vision Transformer (ViT) in performance and efficiency by introducing convolutions into ViT to yield the best of both designs. This is…

Image pyramids are widely adopted in top-performing methods to obtain multi-scale features for precise visual perception and understanding. However, current image pyramids use the same large-scale model to process multiple resolutions of…

Virtual network embedding is one of the key problems of network virtualization. Since virtual network mapping is an NP-hard problem, a lot of research has focused on the evolutionary algorithm's masterpiece genetic algorithm. However, the…

Purpose: Iterative projection reconstruction algorithms are currently the preferred reconstruction method in proton computed tomography (pCT). However, due to inconsistencies in the measured data arising from proton energy straggling and…

Generalizing a pretrained model to unseen datasets without retraining is an essential step toward a foundation model. However, achieving such cross-dataset, fully inductive inference is difficult in graph-structured data where feature…

Effective recognition of spatial patterns and learning their hierarchy is crucial in modern spatial data analysis. Volumetric data applications seek techniques ensuring invariance not only to shifts but also to pattern rotations. While…

Learning transformation invariant representations of visual data is an important problem in computer vision. Deep convolutional networks have demonstrated remarkable results for image and video classification tasks. However, they have…

Transformers have revolutionized performance in Natural Language Processing and Vision, paving the way for their integration with Graph Neural Networks (GNNs). One key challenge in enhancing graph transformers is strengthening the…

Value iteration networks (VINs) enable end-to-end learning for planning tasks by employing a differentiable "planning module" that approximates the value iteration algorithm. However, long-term planning remains a challenge because training…

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…

We study a crucial yet often overlooked issue inherent to Vision Transformers (ViTs): feature maps of these models exhibit grid-like artifacts, which hurt the performance of ViTs in downstream dense prediction tasks such as semantic…

We propose the Interferometric Graph Transform (IGT), which is a new class of deep unsupervised graph convolutional neural network for building graph representations. Our first contribution is to propose a generic, complex-valued spectral…

Transformers are transforming the landscape of computer vision, especially for recognition tasks. Detection transformers are the first fully end-to-end learning systems for object detection, while vision transformers are the first fully…