IEEE

Host-driven In-Network Aggregation on RDMA

Abstract: Large-scale datacenter networks are increasingly using in-network aggregation (INA) and remote direct memory access (RDMA) techniques to accelerate deep neural network (DNN) training.
IEEE

Unsupervised Point Cloud Co-Part Segmentation via Co-Attended Superpoint Generation and Aggregation

Abstract: We propose a co-part segmentation method that takes a set of point clouds of the same category as input where neither a ground truth label nor a prior network is required. With difficulties ...
IEEE

A Graph Aggregation Convolution and Attention Mechanism Based Semantic Segmentation Method for Sparse Lidar Point Cloud Data

Abstract: In recent years, following the development of sensor and computer techniques, it is favored by many fields, i.e. automatic drive, intelligent home, etc., which the deep learning based ...
IEEE

Target Point Cloud Segmentation for Battery Swapping Robot Based on Multiscale Attention Aggregation

Abstract: Rapid and accurate segmentation of 3-D point clouds is critical for optimizing battery-swapping robots and ensuring precise assembly. To address the challenges of computational inefficiency ...
IEEE

MAPANet: A Multi-Scale Attention-Guided Progressive Aggregation Network for Multi-Contrast MRI Super-Resolution

Abstract: Multi-contrast magnetic resonance imaging (MRI) super-resolution (SR), which utilizes complementary information from different contrast images to reconstruct the target images, can provide ...
IEEE

DenseRadar: Dense Radar Generation and Point Consistency Aggregation for 3D Object Detection

Abstract: Accurate environmental perception is critical for autonomous vehicles, typically achieved through multi-sensor fusion. However, existing camera-radar fusion methods often neglect effective ...
IEEE

Two-Phase Sparsification With Secure Aggregation for Privacy-Aware Federated Learning

Abstract: As a typical privacy-aware machine learning paradigm, federated learning (FL) provides facilities to individually train edge clients with their private data and aggregate the central global ...
IEEE

Geometric-Relational Context Aggregation for Indoor Point Cloud Semantic Segmentation

Abstract: To address the limitations of insufficient geometric modeling and inadequate context fusion in indoor point cloud semantic segmentation, we propose Geometric-Relational Context Aggregation ...
IEEE

In-Network Aggregation as a Generic Service for Distributed Applications

Abstract: The performance of distributed applications has long been hindered by network communication, which has emerged as a significant bottleneck. At the core of this issue, the many-to-one incast ...
IEEE

SVFL: Efficient Secure Aggregation and Verification for Cross-Silo Federated Learning

Abstract: Cross-silo federated learning (FL) allows organizations to collaboratively train machine learning (ML) models by sending their local gradients to a server for aggregation, without having to ...
IEEE

Model Reduction and Dynamic Aggregation of Grid-Forming Inverter Networks

Abstract: This paper presents a model-order reduction and dynamic aggregation strategy for grid-forming inverter-based power networks. The reduced-order models preserve the network current dynamics as ...