Related papers: Virtual Width Networks
Virtual wide-area networks (WANs) are WAN-as-a-service cloud offerings that aim to bring the performance benefits of dedicated wide-area interconnects to enterprise customers. In this work, we show that the topology of a virtual WAN can…
The rapid development of large-scale deep learning models questions the affordability of hardware platforms, which necessitates the pruning to reduce their computational and memory footprints. Sparse neural networks as the product, have…
Variational representations of divergences and distances between high-dimensional probability distributions offer significant theoretical insights and practical advantages in numerous research areas. Recently, they have gained popularity in…
As networks grow in size and complexity, backbones become an essential network representation. Indeed, they provide a simplified yet informative overview of the underlying organization by retaining the most significant and structurally…
Current virtual reality systems are typically limited by performance/cost, usability (size), or a combination of both. By using a networked client/server environment, we have solved these limitations for the client. However, in doing so we…
We introduce dense vision transformers, an architecture that leverages vision transformers in place of convolutional networks as a backbone for dense prediction tasks. We assemble tokens from various stages of the vision transformer into…
Visual Transformers (VTs) are emerging as an architectural paradigm alternative to Convolutional networks (CNNs). Differently from CNNs, VTs can capture global relations between image elements and they potentially have a larger…
Since the introduction of the Vision Transformer (ViT), researchers have sought to make ViTs more efficient by removing redundant information in the processed tokens. While different methods have been explored to achieve this goal, we still…
Most artificial networks today rely on dense representations, whereas biological networks rely on sparse representations. In this paper we show how sparse representations can be more robust to noise and interference, as long as the…
Network virtualization enables Internet service providers to run multiple heterogeneous and dedicated network architectures for different customers on a shared substrate. In existing works on virtual network embedding (VNE), each customer…
We present a memory and computation efficient ternary weight networks (TWNs) - with weights constrained to +1, 0 and -1. The Euclidian distance between full (float or double) precision weights and the ternary weights along with a scaling…
There has been a debate on whether to use 2D or 3D deep neural networks for volumetric organ segmentation. Both 2D and 3D models have their advantages and disadvantages. In this paper, we present an alternative framework, which trains 2D…
Network virtualization is an important concept to overcome the ossification of today's Internet as it facilitates innovation also in the network core and as it promises a more efficient use of the given resources and infrastructure. Virtual…
Network virtualization is a technology of running multiple heterogeneous network architecture on a shared substrate network. One of the crucial components in network virtualization is virtual network embedding, which provides a way to…
Recent Large Vision-Language Models (LVLMs) have advanced multi-modal understanding by incorporating finer-grained visual perception and encoding. However, such methods incur significant computational costs due to longer visual token…
While visual imitation learning offers one of the most effective ways of learning from visual demonstrations, generalizing from them requires either hundreds of diverse demonstrations, task specific priors, or large, hard-to-train…
Performance of deep learning models is strongly governed by architectural capacity, with width and depth as primary controls. However, in physical-science applications, models are often compared at a single fixed size or by separating…
3D CNN shows its strong ability in learning spatiotemporal representation in recent video recognition tasks. However, inflating 2D convolution to 3D inevitably introduces additional computational costs, making it cumbersome in practical…
State-of-the-art neural network models estimate large displacement optical flow in multi-resolution and use warping to propagate the estimation between two resolutions. Despite their impressive results, it is known that there are two…
End-to-end performance estimation and measurement of deep neural network (DNN) systems become more important with increasing complexity of DNN systems consisting of hardware and software components. The methodology proposed in this paper…