Search Results for author:
Found 64 papers, 15 papers with code
Adaptive Online Learning of Separable Path Graph Transforms for Intra-prediction
Current video coding standards, including H. 264/AVC, HEVC, and VVC, employ discrete cosine transform (DCT), discrete sine transform (DST), and secondary to Karhunen-Loeve transforms (KLTs) decorrelate the intra-prediction residuals.
Lossy Compression of Adjacency Matrices by Graph Filter Banks
In this paper, we propose a lossy compression of weighted adjacency matrices, where the binary adjacency information is encoded losslessly (so the topological information of the graph is preserved) while the edge weights are compressed lossily.
Fast graph-based denoising for point cloud color information
Second, we propose a fast noise level estimation method using eigenvalues of the covariance matrix on a graph.
Optimizing $k$ in $k$NN Graphs with Graph Learning Perspective
$k$NN is one of the most popular approaches and is widely used in machine learning and signal processing.
Frequency analysis and filter design for directed graphs with polar decomposition
This approach provides a novel interpretation in the node domain and reveals aspects of graph signals that may be overlooked with a singular measure of variation.
Irregularity-Aware Bandlimited Approximation for Graph Signal Interpolation
In most work to date, graph signal sampling and reconstruction algorithms are intrinsically tied to graph properties, assuming bandlimitedness and optimal sampling set choices.
Towards a geometric understanding of Spatio Temporal Graph Convolution Networks
In this paper, we first propose to use a local Dataset Graph (DS-Graph) obtained from the feature representation of input data at each layer to develop an understanding of the layer-wise embedding geometry of the STGCN.
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.
Signal Variation Metrics and Graph Fourier Transforms for Directed Graphs
In this paper we consider the problem of constructing graph Fourier transforms (GFTs) for directed graphs (digraphs), with a focus on developing multiple GFT designs that can capture different types of variation over the digraph node-domain.
Graph Signal Processing: History, Development, Impact, and Outlook
Graph signal processing (GSP) generalizes signal processing (SP) tasks to signals living on non-Euclidean domains whose structure can be captured by a weighted graph.
Joint Graph and Vertex Importance Learning
In this paper, we explore the topic of graph learning from the perspective of the Irregularity-Aware Graph Fourier Transform, with the goal of learning the graph signal space inner product to better model data.
Towards bandwidth estimation for graph signal reconstruction
In numerous graph signal processing applications, data is often missing for a variety of reasons, and predicting the missing data is essential.
Rate-Distortion Optimization With Alternative References For UGC Video Compression
We proposed a geometric criterion for saturation detection that works with rate-distortion optimization, and only requires a few frames from the UGC video.
Image Coding via Perceptually Inspired Graph Learning
Most codec designs rely on the mean squared error (MSE) as a fidelity metric in rate-distortion optimization, which allows to choose the optimal parameters in the transform domain but may fail to reflect perceptual quality.
Study of Manifold Geometry using Multiscale Non-Negative Kernel Graphs
Modern machine learning systems are increasingly trained on large amounts of data embedded in high-dimensional spaces.
Motion estimation and filtered prediction for dynamic point cloud attribute compression
The scheme includes integer-precision motion estimation and an adaptive graph based in-loop filtering scheme for improved attribute prediction.
The Geometry of Self-supervised Learning Models and its Impact on Transfer Learning
Self-supervised learning (SSL) has emerged as a desirable paradigm in computer vision due to the inability of supervised models to learn representations that can generalize in domains with limited labels.
Toward a Geometrical Understanding of Self-supervised Contrastive Learning
When used for transfer learning, the projector is discarded since empirical results show that its representation generalizes more poorly than the encoder's.
Compression of user generated content using denoised references
UGC video is uploaded by users, and then it is re-encoded to be made available at various levels of quality.
Two Channel Filter Banks on Arbitrary Graphs with Positive Semi Definite Variation Operators
Our approach is based on novel graph Fourier transforms (GFTs) given by the generalized eigenvectors of the variation operator.
Hybrid Model-based / Data-driven Graph Transform for Image Coding
Transform coding to sparsify signal representations remains crucial in an image compression pipeline.
Fractional Motion Estimation for Point Cloud Compression
Motivated by the success of fractional pixel motion in video coding, we explore the design of motion estimation with fractional-voxel resolution for compression of color attributes of dynamic 3D point clouds.
Channel redundancy and overlap in convolutional neural networks with channel-wise NNK graphs
Feature spaces in the deep layers of convolutional neural networks (CNNs) are often very high-dimensional and difficult to interpret.
NNK-Means: Data summarization using dictionary learning with non-negative kernel regression
An increasing number of systems are being designed by gathering significant amounts of data and then optimizing the system parameters directly using the obtained data.
Orthogonal Transforms for Signals on Directed Graphs
In this paper we consider the problem of defining transforms for signals on directed graphs, with a specific focus on defective graphs where the corresponding graph operator cannot be diagonalized.
Learning Sparse Graph with Minimax Concave Penalty under Gaussian Markov Random Fields
This paper presents a convex-analytic framework to learn sparse graphs from data.
Graph Signal Processing over a Probability Space of Shift Operators
Each graph topology gives rise to a different shift operator.
Channel-Wise Early Stopping without a Validation Set via NNK Polytope Interpolation
Motivated by our observations, we use CW-DeepNNK to propose a novel early stopping criterion that (i) does not require a validation set, (ii) is based on a task performance metric, and (iii) allows stopping to be reached at different points for each channel.
Cylindrical coordinates for LiDAR point cloud compression
We present an efficient voxelization method to encode the geometry and attributes of 3D point clouds obtained from autonomous vehicles.
Multi-resolution intra-predictive coding of 3D point cloud attributes
We propose an intra frame predictive strategy for compression of 3D point cloud attributes.
DCT and DST Filtering with Sparse Graph Operators
These sparse operators can be viewed as graph filters operating in the DCT domain, which allows us to approximate any DCT graph filter by a MPGF, leading to a design with more degrees of freedom than the conventional PGF approach.
Practical graph signal sampling with log-linear size scaling
Graph signal sampling is the problem of selecting a subset of representative graph vertices whose values can be used to interpolate missing values on the remaining graph vertices.
Pre-demosaic Graph-based Light Field Image Compression
Using a conventional Bayer pattern, data captured at each pixel is a single color component (R, G or B). The sensed data then undergoes demosaicking (interpolation of RGB components per pixel) and conversion to an array of sub-aperture images (SAIs).
Spatio-Temporal Graph Scattering Transform
Although spatio-temporal graph neural networks have achieved great empirical success in handling multiple correlated time series, they may be impractical in some real-world scenarios due to a lack of sufficient high-quality training data.
Representing Deep Neural Networks Latent Space Geometries with Graphs
However, when processing a batch of inputs concurrently, the corresponding set of intermediate representations exhibit relations (what we call a geometry) on which desired properties can be sought.
Learning Sparse Graph Laplacian with K Eigenvector Prior via Iterative GLASSO and Projection
Learning a suitable graph is an important precursor to many graph signal processing (GSP) pipelines, such as graph spectral signal compression and denoising.
Spectral folding and two-channel filter-banks on arbitrary graphs
A major limitation is that this framework can only be applied to the normalized Laplacian of bipartite graphs.
DeepNNK: Explaining deep models and their generalization using polytope interpolation
Modern machine learning systems based on neural networks have shown great success in learning complex data patterns while being able to make good predictions on unseen data points.
BIG-bench Machine Learning
Interpretability Techniques for Deep Learning
+2
Sampling Signals on Graphs: From Theory to Applications
In this article, we review current progress on sampling over graphs focusing on theory and potential applications.
Region adaptive graph fourier transform for 3d point clouds
Since clusters may have a different numbers of points, each block transform must incorporate the relative importance of each coefficient.
Efficient graph construction for image representation
Graphs are useful to interpret widely used image processing methods, e. g., bilateral filtering, or to develop new ones, e. g., kernel based techniques.
Time-Varying Graph Learning with Constraints on Graph Temporal Variation
We propose a novel framework for learning time-varying graphs from spatiotemporal measurements.
Deep geometric knowledge distillation with graphs
Specifically we introduce a graph-based RKD method, in which graphs are used to capture the geometry of latent spaces.
Neighborhood and Graph Constructions using Non-Negative Kernel Regression
Data-driven neighborhood definitions and graph constructions are often used in machine learning and signal processing applications.
Structural Robustness for Deep Learning Architectures
Deep Networks have been shown to provide state-of-the-art performance in many machine learning challenges.
Graph-based Transforms for Video Coding
In many state-of-the-art compression systems, signal transformation is an integral part of the encoding and decoding process, where transforms provide compact representations for the signals of interest.
Graph Based Skeleton Modeling for Human Activity Analysis
Understanding human activity based on sensor information is required in many applications and has been an active research area.
Ranked #4 on
Skeleton Based Action Recognition
on MSR Action3D
Laplacian Networks: Bounding Indicator Function Smoothness for Neural Networks Robustness
For the past few years, Deep Neural Network (DNN) robustness has become a question of paramount importance.
Introducing Graph Smoothness Loss for Training Deep Learning Architectures
We introduce a novel loss function for training deep learning architectures to perform classification.
Laplacian Networks: Bounding Indicator Function Smoothness for Neural Network Robustness
For the past few years, Deep Neural Network (DNN) robustness has become a question of paramount importance.
Active covariance estimation by random sub-sampling of variables
We apply our analysis in an active learning framework, where the expected number of observed variables is small compared to the dimension of the vector of interest, and propose a design of optimal sub-sampling probabilities and an active covariance matrix estimation algorithm.
Graph Learning from Filtered Signals: Graph System and Diffusion Kernel Identification
This paper introduces a novel graph signal processing framework for building graph-based models from classes of filtered signals.
Graph Signal Processing: Overview, Challenges and Applications
Research in Graph Signal Processing (GSP) aims to develop tools for processing data defined on irregular graph domains.
Signal Processing
Learning Graphs with Monotone Topology Properties and Multiple Connected Components
Then, a graph weight estimation (GWE) step is performed by solving a generalized graph Laplacian estimation problem, where edges are constrained by the topology found in the GTI step.
A Sampling Theory Perspective of Graph-based Semi-supervised Learning
In this work, we reinforce this connection by viewing the problem from a graph sampling theoretic perspective, where class indicator functions are treated as bandlimited graph signals (in the eigenvector basis of the graph Laplacian) and label prediction as a bandlimited reconstruction problem.
Graph-Based Manifold Frequency Analysis for Denoising
We propose a new framework for manifold denoising based on processing in the graph Fourier frequency domain, derived from the spectral decomposition of the discrete graph Laplacian.
Graph Learning from Data under Structural and Laplacian Constraints
For the proposed graph learning problems, specialized algorithms are developed by incorporating the graph Laplacian and structural constraints.
Active Learning On Weighted Graphs Using Adaptive And Non-adaptive Approaches
A new sampling algorithm is proposed, which sequentially selects the graph nodes to be sampled, based on an aggressive search for the boundary of the signal over the graph.
Active Learning for Community Detection in Stochastic Block Models
Our main result is to show that, under certain conditions, sampling the labels of a vanishingly small fraction of nodes (a number sub-linear in $n$) is sufficient for exact community detection even when $D(a, b)<1$.
A Probabilistic Interpretation of Sampling Theory of Graph Signals
We give a probabilistic interpretation of sampling theory of graph signals.
Asymptotic Justification of Bandlimited Interpolation of Graph signals for Semi-Supervised Learning
Graph-based methods play an important role in unsupervised and semi-supervised learning tasks by taking into account the underlying geometry of the data set.
Active Semi-Supervised Learning Using Sampling Theory for Graph Signals
The sampling theory for graph signals aims to extend the traditional Nyquist-Shannon sampling theory by allowing us to identify the class of graph signals that can be reconstructed from their values on a subset of vertices.
Localized Iterative Methods for Interpolation in Graph Structured Data
In this paper, we present two localized graph filtering based methods for interpolating graph signals defined on the vertices of arbitrary graphs from only a partial set of samples.
The Emerging Field of Signal Processing on Graphs: Extending High-Dimensional Data Analysis to Networks and Other Irregular Domains
In applications such as social, energy, transportation, sensor, and neuronal networks, high-dimensional data naturally reside on the vertices of weighted graphs.
