Related papers: A Resampling-Based Framework for Network Structure…

Point clouds are an efficient data format for 3D data. However, existing 3D segmentation methods for point clouds either do not model local dependencies \cite{pointnet} or require added computations \cite{kd-net,pointnet2}. This work…

Recent deep-learning-based approaches to single-image reflection removal have shown promising advances, primarily for two reasons: 1) the utilization of recognition-pretrained features as inputs, and 2) the design of dual-stream interaction…

With the advent of high-throughput sequencing (HTS) in molecular biology and medicine, the need for scalable statistical solutions for modeling complex biological systems has become of critical importance. The increasing number of platforms…

We introduce Repetition-Reduction network (RRNet) for resource-constrained depth estimation, offering significantly improved efficiency in terms of computation, memory and energy consumption. The proposed method is based on…

We propose a general method to train a single convolutional neural network which is capable of switching image resolutions at inference. Thus the running speed can be selected to meet various computational resource limits. Networks trained…

Understanding the informative structures of scenes is essential for low-level vision tasks. Unfortunately, it is difficult to obtain a concrete visual definition of the informative structures because influences of visual features are…

Domain Name System (DNS) tunneling remains a covert channel for data exfiltration and command-and-control communication. Although graph-based methods such as GraphTunnel achieve strong accuracy, they introduce significant latency and…

Graph Neural Networks (GNNs) are a promising deep learning approach for circumventing many real-world problems on graph-structured data. However, these models usually have at least one of four fundamental limitations: over-smoothing,…

Current NAS-based semantic segmentation methods focus on accuracy improvements rather than light-weight design. In this paper, we proposed a two-stage framework to design our NAS-based RSPNet model for light-weight semantic segmentation.…

We propose a structured prediction architecture, which exploits the local generic features extracted by Convolutional Neural Networks and the capacity of Recurrent Neural Networks (RNN) to retrieve distant dependencies. The proposed…

Reinforcement Learning (RL) has gained significant momentum in the development of network protocols. However, RL-based protocols are still in their infancy, and substantial research is required to build deployable solutions. Developing a…

Residual Networks (ResNets) have become state-of-the-art models in deep learning and several theoretical studies have been devoted to understanding why ResNet works so well. One attractive viewpoint on ResNet is that it is optimizing the…

The scalable solution of large sparse linear systems is a bottleneck in scientific computing and graph analysis. While algebraic multigrid (AMG) offers optimal linear scaling, its performance is severely constrained by the trade-off between…

Heterogeneous network data with rich nodal information become increasingly prevalent across multidisciplinary research, yet accurately modeling complex nodal heterogeneity and simultaneously selecting influential nodal attributes remains an…

Recent research has shown the great potential of deep learning algorithms in the hyperspectral image (HSI) classification task. Nevertheless, training these models usually requires a large amount of labeled data. Since the collection of…

Graph classification is a crucial task in many real-world multimedia applications, where graphs can represent various multimedia data types such as images, videos, and social networks. Previous efforts have applied graph neural networks…

Recurrent Neural Networks (RNNs) are among the most successful machine learning models for sequence modelling, but tend to suffer from an exponential increase in the number of parameters when dealing with large multidimensional data. To…

Despite the rapid progress of neuromorphic computing, inadequate capacity and insufficient representation power of spiking neural networks (SNNs) severely restrict their application scope in practice. Residual learning and shortcuts have…

NeuroNet is a deep convolutional neural network mimicking multiple popular and state-of-the-art brain segmentation tools including FSL, SPM, and MALPEM. The network is trained on 5,000 T1-weighted brain MRI scans from the UK Biobank Imaging…

The speckle field yielded by disordered media is extensively employed for spectral measurements. Existing speckle reconstructive spectrometers (RSs) implemented by neural networks primarily rely on supervised learning, which necessitates…