Related papers: SlicerNNInteractive: A 3D Slicer extension for nnI…

As the significance of simulation in medical care and intervention continues to grow, it is anticipated that a simplified and low-cost platform can be set up to execute personalized diagnoses and treatments. 3D Slicer can not only perform…

While many systems have been developed to train Graph Neural Networks (GNNs), efficient model inference and evaluation remain to be addressed. For instance, using the widely adopted node-wise approach, model evaluation can account for up to…

This work presents a multi-layer DNN scheduling framework as an extension of OctopuScheduler, providing an end-to-end flow from PyTorch models to inference on a single SpiNNaker2 chip. Together with a front-end comprised of quantization and…

Although deep neural networks have provided impressive gains in performance, these improvements often come at the cost of increased computational complexity and expense. In many cases, such as 3D volume or video classification tasks, not…

Object detection using deep neural networks (DNNs) involves a huge amount of computation which impedes its implementation on resource/energy-limited user-end devices. The reason for the success of DNNs is due to having knowledge over all…

The proliferation of edge devices necessitates efficient computational architectures for lightweight tasks, particularly deep neural network (DNN) inference. Traditional NPUs, though effective for such operations, face challenges in power,…

Deep neural networks (DNN) are powerful models for many pattern recognition tasks, yet their high computational complexity and memory requirement limit them to applications on high-performance computing platforms. In this paper, we propose…

We present a novel real-time line segment detection scheme called Line Graph Neural Network (LGNN). Existing approaches require a computationally expensive verification or postprocessing step. Our LGNN employs a deep convolutional neural…

Retinal imaging is a critical, non-invasive modality for the early detection and monitoring of ocular and systemic diseases. Deep learning, particularly convolutional neural networks (CNNs), has significant progress in automated retinal…

Performances on standard 3D point cloud benchmarks have plateaued, resulting in oversized models and complex network design to make a fractional improvement. We present an alternative to enhance existing deep neural networks without any…

The challenging requirements of 5G--from both the applications and the architecture perspectives--motivate the need to explore the feasibility of delivering services over new network architectures. As 5G proposes application-centric network…

We propose distributed deep neural networks (DDNNs) over distributed computing hierarchies, consisting of the cloud, the edge (fog) and end devices. While being able to accommodate inference of a deep neural network (DNN) in the cloud, a…

The demand for high-speed, low-latency, and energy-efficient object detection in autonomous systems -- such as advanced driver-assistance systems (ADAS), unmanned aerial vehicles (UAVs), and Industry 4.0 robotics -- has exposed the…

We introduce Deformable Convolution v4 (DCNv4), a highly efficient and effective operator designed for a broad spectrum of vision applications. DCNv4 addresses the limitations of its predecessor, DCNv3, with two key enhancements: 1.…

Ubiquitous artificial intelligence (AI) is considered one of the key services in 6G systems. AI services typically rely on deep neural network (DNN) requiring heavy computation. Hence, in order to support ubiquitous AI, it is crucial to…

We propose a class of interleavers for a novel deep neural network (DNN) architecture that uses algorithmically pre-determined, structured sparsity to significantly lower memory and computational requirements, and speed up training. The…

We design deep neural networks (DNNs) and corresponding networks' splittings to distribute DNNs' workload to camera sensors and a centralized aggregator on head mounted devices to meet system performance targets in inference accuracy and…

We present NeRFEditor, an efficient learning framework for 3D scene editing, which takes a video captured over 360{\deg} as input and outputs a high-quality, identity-preserving stylized 3D scene. Our method supports diverse types of…

Many interactive image segmentation techniques are based on semi-supervised learning. The user may label some pixels from each object and the SSL algorithm will propagate the labels from the labeled to the unlabeled pixels, finding object…

In this study, we introduce Convolutional Transformer Neural Collaborative Filtering (CTNCF), a novel approach aimed at enhancing recommendation systems by effectively capturing high-order structural information in user-item interactions.…