Search Results for author:
Found 18 papers, 5 papers with code
Contrastive Learning for Regression on Hyperspectral Data
Contrastive learning has demonstrated great effectiveness in representation learning especially for image classification tasks.
SynWoodScape: Synthetic Surround-view Fisheye Camera Dataset for Autonomous Driving
In this work, we release a synthetic version of the surround-view dataset, covering many of its weaknesses and extending it.
Effect of Prior-based Losses on Segmentation Performance: A Benchmark
To enforce anatomical plausibility, recent research studies have focused on incorporating prior knowledge such as object shape or boundary, as constraints in the loss function.
Breaking the Limits of Message Passing Graph Neural Networks
Since the Message Passing (Graph) Neural Networks (MPNNs) have a linear complexity with respect to the number of nodes when applied to sparse graphs, they have been widely implemented and still raise a lot of interest even though their theoretical expressive power is limited to the first order Weisfeiler-Lehman test (1-WL).
Analyzing the Expressive Power of Graph Neural Networks in a Spectral Perspective
Since the graph isomorphism problem is NP-intermediate, and Weisfeiler-Lehman (WL) test can give sufficient but not enough evidence in polynomial time, the theoretical power of GNNs is usually evaluated by the equivalence of WL-test order, followed by an empirical analysis of the models on some reference inductive and transductive datasets.
High-level Prior-based Loss Functions for Medical Image Segmentation: A Survey
Today, deep convolutional neural networks (CNNs) have demonstrated state of the art performance for supervised medical image segmentation, across various imaging modalities and tasks.
Statistical learning for sensor localization in wireless networks
Indoor localization has become an important issue for wireless sensor networks.
Bridging the Gap Between Spectral and Spatial Domains in Graph Neural Networks
Moreover, the proposed framework is used to design new convolutions in spectral domain with a custom frequency profile while applying them in the spatial domain.
Ranked #1 on
Node Classification
on Cora: fixed 20 node per class
Graph Kernels Based on Linear Patterns: Theoretical and Experimental Comparisons
In this work, we propose a thorough investigation and comparison of graph kernels based on different linear patterns, namely walks and paths.
Ranked #36 on
Graph Classification
on MUTAG
Une véritable approche $\ell_0$ pour l'apprentissage de dictionnaire
Sparse representation learning has recently gained a great success in signal and image processing, thanks to recent advances in dictionary learning.
Maximum Correntropy Unscented Filter
To improve the robustness of the UKF against impulsive noises, a new filter for nonlinear systems is proposed in this work, namely the maximum correntropy unscented filter (MCUF).
Correntropy Maximization via ADMM - Application to Robust Hyperspectral Unmixing
In hyperspectral images, some spectral bands suffer from low signal-to-noise ratio due to noisy acquisition and atmospheric effects, thus requiring robust techniques for the unmixing problem.
Bi-Objective Nonnegative Matrix Factorization: Linear Versus Kernel-Based Models
Nonnegative matrix factorization (NMF) is a powerful class of feature extraction techniques that has been successfully applied in many fields, namely in signal and image processing.
Entropy of Overcomplete Kernel Dictionaries
More generally than the linear decomposition, overcomplete kernel dictionaries provide an elegant nonlinear extension by defining the atoms through a mapping kernel function (e. g., the gaussian kernel).
Analyzing sparse dictionaries for online learning with kernels
Many signal processing and machine learning methods share essentially the same linear-in-the-parameter model, with as many parameters as available samples as in kernel-based machines.
Approximation errors of online sparsification criteria
For this purpose, several online sparsification criteria have been proposed to restrict the model definition on a subset of samples.
Kernel Nonnegative Matrix Factorization Without the Curse of the Pre-image - Application to Unmixing Hyperspectral Images
The nonnegative matrix factorization (NMF) is widely used in signal and image processing, including bio-informatics, blind source separation and hyperspectral image analysis in remote sensing.
An eigenanalysis of data centering in machine learning
Furthermore, we explore the outer product matrices, by providing several results connecting the largest eigenvectors of the covariance matrix and its non-centered counterpart.
