100 citations · 175 across the 12 of their papers we have counts for
12 papers
A Review of Benchmarks for Visual Defect Detection in the Manufacturing Industry
Philippe Carvalho, Alexandre Durupt, Yves Grandvalet
The field of industrial defect detection using machine learning and deep learning is a subject of active research. Datasets, also called benchmarks, are used to compare and assess…
Learning from missing data with the Latent Block Model
Gabriel Frisch, Jean-Benoist Léger, Yves Grandvalet
Missing data can be informative. Ignoring this information can lead to misleading conclusions when the data model does not allow information to be extracted from the missing data.…
Driving among Flatmobiles: Bird-Eye-View occupancy grids from a monocular camera for holistic trajectory planning
Abdelhak Loukkal, Yves Grandvalet, Tom Drummond +1
Camera-based end-to-end driving neural networks bring the promise of a low-cost system that maps camera images to driving control commands. These networks are appealing because the…
Representation Transfer by Optimal Transport
Xuhong Li, Yves Grandvalet, Rémi Flamary +2
Learning generic representations with deep networks requires massive training samples and significant computer resources. To learn a new specific task, an important issue is to tra…
Explicit Inductive Bias for Transfer Learning with Convolutional Networks
Xuhong Li, Yves Grandvalet, Franck Davoine
In inductive transfer learning, fine-tuning pre-trained convolutional networks substantially outperforms training from scratch. When using fine-tuning, the underlying assumption is…
Combining Two And Three-Way Embeddings Models for Link Prediction in Knowledge Bases
Alberto Garcia-Duran, Antoine Bordes, Nicolas Usunier +1
This paper tackles the problem of endogenous link prediction for Knowledge Base completion. Knowledge Bases can be represented as directed graphs whose nodes correspond to entities…
Beyond Support in Two-Stage Variable Selection
Jean-Michel Bécu, Yves Grandvalet, Christophe Ambroise +1
Numerous variable selection methods rely on a two-stage procedure, where a sparsity-inducing penalty is used in the first stage to predict the support, which is then conveyed to th…
Theory of Optimizing Pseudolinear Performance Measures: Application to F-measure
Shameem A Puthiya Parambath, Nicolas Usunier, Yves Grandvalet
Non-linear performance measures are widely used for the evaluation of learning algorithms. For example, -measure is a commonly used performance measure for classification proble…
Sparsity by Worst-Case Penalties
Yves Grandvalet, Julien Chiquet, Christophe Ambroise
This paper proposes a new interpretation of sparse penalties such as the elastic-net and the group-lasso. Beyond providing a new viewpoint on these penalization schemes, our approa…
An Efficient Approach to Sparse Linear Discriminant Analysis
Luis Francisco Sanchez Merchante, Yves Grandvalet, Gerrad Govaert
We present a novel approach to the formulation and the resolution of sparse Linear Discriminant Analysis (LDA). Our proposal, is based on penalized Optimal Scoring. It has an exact…
Sparsity with sign-coherent groups of variables via the cooperative-Lasso
Julien Chiquet, Yves Grandvalet, Camille Charbonnier
We consider the problems of estimation and selection of parameters endowed with a known group structure, when the groups are assumed to be sign-coherent, that is, gathering either…
Inferring Multiple Graphical Structures
Julien Chiquet, Yves Grandvalet, Christophe Ambroise
Gaussian Graphical Models provide a convenient framework for representing dependencies between variables. Recently, this tool has received a high interest for the discovery of biol…