Search Results for author:
Found 51 papers, 13 papers with code
PointDifformer: Robust Point Cloud Registration With Neural Diffusion and Transformer
Point cloud registration is a fundamental technique in 3-D computer vision with applications in graphics, autonomous driving, and robotics.
Coupling Graph Neural Networks with Fractional Order Continuous Dynamics: A Robustness Study
In this work, we rigorously investigate the robustness of graph neural fractional-order differential equation (FDE) models.
PosDiffNet: Positional Neural Diffusion for Point Cloud Registration in a Large Field of View with Perturbations
We leverage a graph neural partial differential equation (PDE) based on Beltrami flow to obtain high-dimensional features and position embeddings for point clouds.
DistilVPR: Cross-Modal Knowledge Distillation for Visual Place Recognition
The utilization of multi-modal sensor data in visual place recognition (VPR) has demonstrated enhanced performance compared to single-modal counterparts.
Towards Neuromorphic Compression based Neural Sensing for Next-Generation Wireless Implantable Brain Machine Interface
Furthermore, we use accuracy, sensitivity, and false detection rate to understand the effect of compression on downstream iBMI tasks, specifically, spike detection.
Modeling Sparse Graph Sequences and Signals Using Generalized Graphons
Our signal processing framework provides a comprehensive approach to analyzing and processing signals on graph sequences, even if they are sparse.
Image Patch-Matching with Graph-Based Learning in Street Scenes
Matching landmark patches from a real-time image captured by an on-vehicle camera with landmark patches in an image database plays an important role in various computer perception tasks for autonomous driving.
RobustMat: Neural Diffusion for Street Landmark Patch Matching under Challenging Environments
For autonomous vehicles (AVs), visual perception techniques based on sensors like cameras play crucial roles in information acquisition and processing.
Graph Neural Networks with a Distribution of Parametrized Graphs
Traditionally, graph neural networks have been trained using a single observed graph.
A sampling construction of graphon 1-norm convergence
The note also contains errata of the previous version of the note.
Adversarial Robustness in Graph Neural Networks: A Hamiltonian Approach
Graph neural networks (GNNs) are vulnerable to adversarial perturbations, including those that affect both node features and graph topology.
Spectral Convergence of Simplicial Complex Signals
We recall the notion of a complexon as the limit of a simplicial complex sequence [1].
Generalized Graphon Process: Convergence of Graph Frequencies in Stretched Cut Distance
This random graph process converges to the generalized graphon in stretched cut distance.
Kernel Based Reconstruction for Generalized Graph Signal Processing
In this paper, we study GGSP signal reconstruction as a kernel ridge regression (KRR) problem.
The faces of Convolution: from the Fourier theory to algebraic signal processing
In this expository article, we provide a self-contained overview of the notion of convolution embedded in different theories: from the classical Fourier theory to the theory of algebraic signal processing.
Approximate Maximum-Likelihood RIS-Aided Positioning
In this paper, we develop a RIS-aided positioning framework to locate a UE in environments where the LOS path may or may not be available.
Node Embedding from Neural Hamiltonian Orbits in Graph Neural Networks
In the graph node embedding problem, embedding spaces can vary significantly for different data types, leading to the need for different GNN model types.
Graph Neural Convection-Diffusion with Heterophily
Graph neural networks (GNNs) have shown promising results across various graph learning tasks, but they often assume homophily, which can result in poor performance on heterophilic graphs.
Generalized signals on simplicial complexes
Topological signal processing (TSP) over simplicial complexes typically assumes observations associated with the simplicial complexes are real scalars.
Leveraging Label Non-Uniformity for Node Classification in Graph Neural Networks
We introduce the key notion of label non-uniformity, which is derived from the Wasserstein distance between the softmax distribution of the logits and the uniform distribution.
Distributional Signals for Node Classification in Graph Neural Networks
In graph neural networks (GNNs), both node features and labels are examples of graph signals, a key notion in graph signal processing (GSP).
HypLiLoc: Towards Effective LiDAR Pose Regression with Hyperbolic Fusion
LiDAR relocalization plays a crucial role in many fields, including robotics, autonomous driving, and computer vision.
Node-Specific Space Selection via Localized Geometric Hyperbolicity in Graph Neural Networks
However, a graph can have hyperbolic and Euclidean geometries at different regions of the graph.
Node Embedding from Hamiltonian Information Propagation in Graph Neural Networks
Graph neural networks (GNNs) have achieved success in various inference tasks on graph-structured data.
Graph signal processing with categorical perspective
In this paper, we propose a framework for graph signal processing using category theory.
On distributional graph signals
We develop signal processing tools to study the new notion of distributional graph signals.
RobustLoc: Robust Camera Pose Regression in Challenging Driving Environments
Experiments demonstrate that RobustLoc surpasses current state-of-the-art camera pose regression models and achieves robust performance in various environments.
Ranked #1 on
Visual Localization
on Oxford RobotCar Full
On semi shift invariant graph filters
In graph signal processing, one of the most important subjects is the study of filters, i. e., linear transformations that capture relations between graph signals.
On the Robustness of Graph Neural Diffusion to Topology Perturbations
In this work, we explore the robustness properties of graph neural PDEs.
SGAT: Simplicial Graph Attention Network
In this paper, we present Simplicial Graph Attention Network (SGAT), a simplicial complex approach to represent such high-order interactions by placing features from non-target nodes on the simplices.
Abstract message passing and distributed graph signal processing
Graph signal processing is a framework to handle graph structured data.
Building Facade Parsing R-CNN
Building facade parsing, which predicts pixel-level labels for building facades, has applications in computer vision perception for autonomous vehicle (AV) driving.
To further understand graph signals
Graph signal processing (GSP) is a framework to analyze and process graph-structured data.
Wide-Sense Stationarity in Generalized Graph Signal Processing
We consider statistical graph signal processing (GSP) in a generalized framework where each vertex of a graph is associated with an element from a Hilbert space.
Using Reconfigurable Intelligent Surfaces for UE Positioning in mmWave MIMO Systems
We develop a RIS-aided positioning framework to locate a UE in environments where the LOS path may or may not be available.
Stable Neural ODE with Lyapunov-Stable Equilibrium Points for Defending Against Adversarial Attacks
By ensuring that the equilibrium points of the ODE solution used as part of SODEF is Lyapunov-stable, the ODE solution for an input with a small perturbation converges to the same solution as the unperturbed input.
Graph Signal Processing over a Probability Space of Shift Operators
Each graph topology gives rise to a different shift operator.
Learning on heterogeneous graphs using high-order relations
A heterogeneous graph consists of different vertices and edges types.
Signal processing with a distribution of graph operators
In this paper, we develop a signal processing framework of a network without explicit knowledge of the network topology.
Sampling Theory of Bandlimited Continuous-Time Graph Signals
A continuous-time graph signal can be viewed as a time series of graph signals.
Data-driven Regularized Inference Privacy
We develop an inference privacy framework based on the variational method and include maximum mean discrepancy and domain adaption as techniques to regularize the domain of the sanitized data to ensure its legacy compatibility.
Attentive Graph Neural Networks for Few-Shot Learning
Graph Neural Networks (GNN) has demonstrated the superior performance in many challenging applications, including the few-shot learning tasks.
Subgraph Signal Processing
Graph signal processing, like the graph Fourier transform, requires the full graph signal at every vertex of the graph.
Signal processing on simplicial complexes
In this paper, we develop a signal processing framework on simplicial complexes, such that we recover the traditional GSP theory when restricted to signals on graphs.
Error-Correcting Output Codes with Ensemble Diversity for Robust Learning in Neural Networks
Though deep learning has been applied successfully in many scenarios, malicious inputs with human-imperceptible perturbations can make it vulnerable in real applications.
Learning Orthogonal Projections in Linear Bandits
In the case where each arm is chosen from an infinite compact set, our strategy achieves $O(n^{2/3}(\log{n})^{1/2})$ regret.
An Unsupervised Bayesian Neural Network for Truth Discovery in Social Networks
An autoencoder learns the complex relationships between event truths, agent reliabilities and agent observations.
GFCN: A New Graph Convolutional Network Based on Parallel Flows
In view of the huge success of convolution neural networks (CNN) for image classification and object recognition, there have been attempts to generalize the method to general graph-structured data.
Task Recommendation in Crowdsourcing Based on Learning Preferences and Reliabilities
We develop three task recommendation strategies to determine the number of gold tasks for different task categories, and show that they are order optimal.
Using Social Network Information in Bayesian Truth Discovery
We incorporate knowledge of the agents' social network in our truth discovery framework and develop Laplace variational inference methods to estimate agents' reliabilities, communities, and the event states.
Sequential Multi-Class Labeling in Crowdsourcing
As workers may be unreliable, we propose to perform sequential questioning in which the questions posed to the workers are designed based on previous questions and answers.
