Search Results for author:
Found 27 papers, 9 papers with code
Gaussian-Smoothed Sliced Probability Divergences
We particularly focus on the Gaussian smoothed sliced Wasserstein distance and prove that it converges with a rate $O(n^{-1/2})$.
Adversarial Semi-Supervised Domain Adaptation for Semantic Segmentation: A New Role for Labeled Target Samples
Adversarial learning baselines for domain adaptation (DA) approaches in the context of semantic segmentation are under explored in semi-supervised framework.
Fast Optimal Transport through Sliced Wasserstein Generalized Geodesics
Wasserstein distance (WD) and the associated optimal transport plan have been proven useful in many applications where probability measures are at stake.
Physically-admissible polarimetric data augmentation for road-scene analysis
Polarimetric imaging, along with deep learning, has shown improved performances on different tasks including scene analysis.
Statistical and Topological Properties of Gaussian Smoothed Sliced Probability Divergences
In this paper, we analyze the theoretical properties of this distance as well as those of generalized versions denoted as Gaussian smoothed sliced divergences.
Unbalanced Optimal Transport through Non-negative Penalized Linear Regression
In particular, we consider majorization-minimization which leads in our setting to efficient multiplicative updates for a variety of penalties.
Heterogeneous Wasserstein Discrepancy for Incomparable Distributions
We provide a theoretical analysis of this new divergence, called $\textit{heterogeneous Wasserstein discrepancy (HWD)}$, and we show that it preserves several interesting properties including rotation-invariance.
From SIR to SEAIRD: a novel data-driven modeling approach based on the Grey-box System Theory to predict the dynamics of COVID-19
When applied to Brazil's cases, SEAIRD produced an excellent agreement to the data, with an %coefficient of determination $R^2$ $\geq 90\%$.
Partial Optimal Tranport with applications on Positive-Unlabeled Learning
Classical optimal transport problem seeks a transportation map that preserves the total mass between two probability distributions, requiring their masses to be equal.
Open Set Domain Adaptation using Optimal Transport
We present a 2-step optimal transport approach that performs a mapping from a source distribution to a target distribution.
Provably Convergent Working Set Algorithm for Non-Convex Regularized Regression
Owing to their statistical properties, non-convex sparse regularizers have attracted much interest for estimating a sparse linear model from high dimensional data.
Optimal Transport for Conditional Domain Matching and Label Shift
We address the problem of unsupervised domain adaptation under the setting of generalized target shift (joint class-conditional and label shifts).
Object Detection in the DCT Domain: is Luminance the Solution?
To gain in efficiency, this paper proposes to take advantage of the compressed representation of images to carry out object detection usable in constrained resources conditions.
Foreground-Background Ambient Sound Scene Separation
Ambient sound scenes typically comprise multiple short events occurring on top of a somewhat stationary background.
Theoretical Guarantees for Bridging Metric Measure Embedding and Optimal Transport
Unlike Gromov-Wasserstein (GW) distance which compares pairwise distances of elements from each distribution, we consider a method allowing to embed the metric measure spaces in a common Euclidean space and compute an optimal transport (OT) on the embedded distributions.
Partial Optimal Transport with Applications on Positive-Unlabeled Learning
In this paper, we address the partial Wasserstein and Gromov-Wasserstein problems and propose exact algorithms to solve them.
Pixel-wise Conditioned Generative Adversarial Networks for Image Synthesis and Completion
We investigate the influence of this regularization term on the quality of the generated images and the fulfillment of the given pixel constraints.
Pixel-wise Conditioning of Generative Adversarial Networks
In this paper, we study the effectiveness of conditioning GANs by adding an explicit regularization term to enforce pixel-wise conditions when very few pixel values are provided.
Screening Sinkhorn Algorithm for Regularized Optimal Transport
We introduce in this paper a novel strategy for efficiently approximating the Sinkhorn distance between two discrete measures.
Dilated Spatial Generative Adversarial Networks for Ergodic Image Generation
In combination with convolutional (for the discriminator) and de-convolutional (for the generator) layers, they are particularly suitable for image generation, especially of natural scenes.
Fast object detection in compressed JPEG Images
Object detection in still images has drawn a lot of attention over past few years, and with the advent of Deep Learning impressive performances have been achieved with numerous industrial applications.
Screening Rules for Lasso with Non-Convex Sparse Regularizers
Leveraging on the convexity of the Lasso problem , screening rules help in accelerating solvers by discarding irrelevant variables, during the optimization process.
Gradient-based deterministic inversion of geophysical data with Generative Adversarial Networks: is it feasible?
Global probabilistic inversion within the latent space learned by Generative Adversarial Networks (GAN) has been recently demonstrated (Laloy et al., 2018).
Geophysics
An efficient supervised dictionary learning method for audio signal recognition
Motivated by this need of a principled framework across domain applications for machine listening, we propose a generic and data-driven representation learning approach.
Importance sampling strategy for non-convex randomized block-coordinate descent
As the number of samples and dimensionality of optimization problems related to statistics an machine learning explode, block coordinate descent algorithms have gained popularity since they reduce the original problem to several smaller ones.
Histogram of gradients of Time-Frequency Representations for Audio scene detection
This paper addresses the problem of audio scenes classification and contributes to the state of the art by proposing a novel feature.
DC Proximal Newton for Non-Convex Optimization Problems
We introduce a novel algorithm for solving learning problems where both the loss function and the regularizer are non-convex but belong to the class of difference of convex (DC) functions.
